Toolathlon

price-comparison

Read our ten product prices out of a CSV and the competitor's out of a PDF, match them up, and write product name, both prices and the difference into BigQuery as bigquery_pricing_analysis.analysis.

Task Prompt

As a member of the market analysis team, you are urgently tasked with analyzing the price differences between our core product line and our primary competitor, FutureGadget. We have scraped pricing information from our competitor's website (stored in PDF format), and we have also obtained our corresponding product prices from the internal file, internal_pricing_sheet.xlsx. Finally, please combine and process these two sets of data, calculate the price difference, and store the final comparison results (including product name, our price, competitor's price, and price difference) in BigQuery for management decision-making. Please refer to the workspace file requirements.md for storage format requirements.

VFS.md

---
name: workspace-filesystem
description: The virtual filesystem layout of this workspace.
---

# Virtual Filesystem

You work in a terminal over a virtual filesystem. Read files with shell
commands; service operations are listed in SKILL.md.

| Path | Description |
|---|---|
| `/workspace` | Agent workspace; current directory and home (`~`). |
| `/tmp` | Temporary files. |
| `/dev` | Device files: `null` and `zero` (mounted automatically). |

name	workspace-filesystem
description	The virtual filesystem layout of this workspace.

Virtual Filesystem

You work in a terminal over a virtual filesystem. Read files with shell commands; service operations are listed in SKILL.md.

Path	Description
`/workspace`	Agent workspace; current directory and home (`~`).
`/tmp`	Temporary files.
`/dev`	Device files: `null` and `zero` (mounted automatically).

SKILL.md

---
name: workspace-commands
description: The shell commands, task tools, and python3 interpreter available in this workspace.
---

# Available commands

Standard Unix commands, among them:

    cat  head  tail  ls  find  grep  wc  sort  uniq  cut  tr  sed  awk
    diff  tee  xargs  jq  unzip  curl

with pipes, `>` redirection, `$(...)` substitution and `$'...'`.

The task CLIs below are registered with this shell rather than installed
as files; do not inspect them with `which`, `file` or `/usr/bin`.

## pdf-tools

Use `pdf-tools <command> '<JSON arguments>'`. Run
`pdf-tools <command> --help` to get more information.

| Command | Arguments | Description |
|---|---|---|
| `pdf-tools read-pdf-pages` | `{pdf_file_path: str, start_page?: int = 1, end_page?: int = 1}` | Read content from PDF file for specified page range. Supports both local file paths and URLs. For URLs, the PDF will be downloaded to a temporary directory and cached for future use. Note: Avoid reading too many pages at once (recommended: <50 pages) to prevent errors. Args: pdf_file_path: Path to the PDF file or URL to PDF start_page: Starting page number (default: 1) end_page: Ending page number (default: 1) Returns: Extracted text content from the specified pages |
| `pdf-tools get-pdf-info` | `{pdf_file_path: str}` | Get basic information about a PDF file including page count. Supports both local file paths and URLs. For URLs, the PDF will be downloaded to a temporary directory and cached for future use. Args: pdf_file_path: Path to the PDF file or URL to PDF Returns: Basic information about the PDF file |
| `pdf-tools merge-pdfs` | `{pdf_paths: list[str], output_path: str}` | Merge multiple PDF files into one. Supports both local file paths and URLs. URLs will be downloaded to temporary files before merging. Mixed local and URL paths are supported. Args: pdf_paths: List of paths to PDF files to merge (in order) - can include URLs output_path: Path where the merged PDF will be saved (must be local path) Returns: Success message with merge details or error message |
| `pdf-tools extract-pdf-pages` | `{source_path: str, page_numbers: list[int], output_path: str}` | Extract specific pages from a PDF and create a new PDF. Supports URLs for source PDF. The source PDF will be downloaded to a temporary directory if it's a URL. Output path must be a local file path. Args: source_path: Path to the source PDF file or URL to PDF page_numbers: List of page numbers to extract (1-indexed) output_path: Path where the new PDF will be saved (must be local path) Returns: Success message with extraction details or error message |
| `pdf-tools search-pdf-content` | `{pdf_file_path: str, pattern: str, page_size?: int = 10}` | Search for regex pattern in PDF content and return paginated results. Supports both local file paths and URLs. For URLs, the PDF will be downloaded to a temporary directory and cached for future use. Args: pdf_file_path: Path to the PDF file or URL to PDF pattern: Regular expression pattern to search for page_size: Number of results per page (10-50, default: 10) Returns: Search results with UUID for pagination, or error message |
| `pdf-tools search-pdf-next-page` | `{search_id: str}` | Get next page of search results. Args: search_id: Search session ID from previous search Returns: Next page of search results or error message |
| `pdf-tools search-pdf-prev-page` | `{search_id: str}` | Get previous page of search results. Args: search_id: Search session ID from previous search Returns: Previous page of search results or error message |
| `pdf-tools search-pdf-go-page` | `{search_id: str, page_number: int}` | Go to specific page of search results. Args: search_id: Search session ID from previous search page_number: Page number to go to (1-indexed) Returns: Specified page of search results or error message |
| `pdf-tools search-pdf-info` | `{search_id: str}` | Get information about a search session. Args: search_id: Search session ID from previous search Returns: Information about the search session |

## google-cloud

Use `google-cloud <command> '<JSON arguments>'`. Run
`google-cloud <command> --help` to get more information.

| Command | Arguments | Description |
|---|---|---|
| `google-cloud bigquery-run-query` | `{query: str, dry_run?: bool = false, max_results?: int = 1000}` | Execute a BigQuery SQL query Args: query: SQL query to execute dry_run: If True, only validate query without running it max_results: Maximum number of results to return (default: 1000) Returns: Query results or error message |
| `google-cloud bigquery-list-datasets` | `{}` | List all BigQuery datasets in the project Returns: List of datasets or error message |
| `google-cloud bigquery-create-dataset` | `{dataset_id: str, description?: str = "", location?: str = "US"}` | Create a new BigQuery dataset Args: dataset_id: ID for the new dataset description: Optional description for the dataset location: Dataset location (default: US) Returns: Success message or error |
| `google-cloud bigquery-get-dataset-info` | `{dataset_id: str}` | Get detailed information about a BigQuery dataset Args: dataset_id: ID of the dataset Returns: Dataset information or error message |
| `google-cloud bigquery-load-csv-data` | `{dataset_id: str, table_id: str, csv_file_path: str, skip_header?: bool = true, write_mode?: str = "WRITE_TRUNCATE"}` | Load data from CSV file to BigQuery table Args: dataset_id: Dataset ID table_id: Table ID csv_file_path: Path to CSV file skip_header: Whether to skip the first row (header) write_mode: Write mode (WRITE_TRUNCATE, WRITE_APPEND, WRITE_EMPTY) Returns: Success message or error |
| `google-cloud bigquery-export-table` | `{dataset_id: str, table_id: str, destination_bucket: str, destination_path: str, file_format?: str = "CSV"}` | Export BigQuery table to Cloud Storage Args: dataset_id: Dataset ID table_id: Table ID destination_bucket: Destination bucket name destination_path: Destination path in bucket file_format: Export format (CSV, JSON, AVRO) Returns: Success message or error |
| `google-cloud bigquery-list-jobs` | `{max_results?: int = 50, state_filter?: str = ""}` | List BigQuery jobs Args: max_results: Maximum number of jobs to return state_filter: Filter by job state (RUNNING, DONE, PENDING) Returns: List of jobs or error message |
| `google-cloud bigquery-cancel-job` | `{job_id: str}` | Cancel a BigQuery job Args: job_id: ID of the job to cancel Returns: Success message or error |
| `google-cloud storage-list-buckets` | `{}` | List all Cloud Storage buckets Returns: List of buckets or error message |
| `google-cloud storage-create-bucket` | `{bucket_name: str, location?: str = "US"}` | Create a new Cloud Storage bucket Args: bucket_name: Name for the new bucket location: Location for the bucket (default: US) Returns: Success message or error |
| `google-cloud storage-list-objects` | `{bucket_name: str, prefix?: str = ""}` | List objects in a Cloud Storage bucket Args: bucket_name: Name of the bucket prefix: Optional prefix to filter objects Returns: List of objects or error message |
| `google-cloud storage-upload-file` | `{bucket_name: str, source_file_path: str, destination_blob_name: str}` | Upload a file to Cloud Storage bucket Args: bucket_name: Name of the bucket source_file_path: Local path to the file to upload destination_blob_name: Name for the blob in the bucket Returns: Success message or error |
| `google-cloud storage-download-file` | `{bucket_name: str, source_blob_name: str, destination_file_path: str}` | Download a file from Cloud Storage bucket Args: bucket_name: Name of the bucket source_blob_name: Name of the blob in the bucket destination_file_path: Local path where to save the file Returns: Success message or error |
| `google-cloud storage-delete-object` | `{bucket_name: str, blob_name: str}` | Delete an object from Cloud Storage bucket Args: bucket_name: Name of the bucket blob_name: Name of the blob to delete Returns: Success message or error |
| `google-cloud storage-get-bucket-info` | `{bucket_name: str}` | Get detailed information about a Cloud Storage bucket Args: bucket_name: Name of the bucket Returns: Bucket information or error message |
| `google-cloud storage-generate-signed-url` | `{bucket_name: str, blob_name: str, expiration_minutes?: int = 60, method?: str = "GET"}` | Generate a signed URL for temporary access to a Cloud Storage object Args: bucket_name: Name of the bucket blob_name: Name of the blob expiration_minutes: URL expiration time in minutes (default: 60) method: HTTP method (GET, PUT, POST, DELETE) Returns: Signed URL or error message |
| `google-cloud storage-copy-object` | `{source_bucket: str, source_blob: str, dest_bucket: str, dest_blob: str}` | Copy an object between Cloud Storage buckets Args: source_bucket: Source bucket name source_blob: Source blob name dest_bucket: Destination bucket name dest_blob: Destination blob name Returns: Success message or error |
| `google-cloud storage-move-object` | `{source_bucket: str, source_blob: str, dest_bucket: str, dest_blob: str}` | Move an object between Cloud Storage buckets Args: source_bucket: Source bucket name source_blob: Source blob name dest_bucket: Destination bucket name dest_blob: Destination blob name Returns: Success message or error |
| `google-cloud storage-enable-versioning` | `{bucket_name: str, enabled?: bool = true}` | Enable or disable versioning for a Cloud Storage bucket Args: bucket_name: Name of the bucket enabled: Whether to enable (True) or disable (False) versioning Returns: Success message or error |
| `google-cloud storage-get-bucket-size` | `{bucket_name: str}` | Get size statistics for a Cloud Storage bucket Args: bucket_name: Name of the bucket Returns: Bucket size information or error message |
| `google-cloud storage-set-bucket-lifecycle` | `{bucket_name: str, age_days?: int = 30, action?: str = "Delete"}` | Set lifecycle rules for a Cloud Storage bucket Args: bucket_name: Name of the bucket age_days: Age in days after which to apply the action action: Action to take (Delete, SetStorageClass) Returns: Success message or error |
| `google-cloud logging-write-log` | `{log_name: str, message: str, severity?: str = "INFO"}` | Write a log entry to Cloud Logging Args: log_name: Name of the log message: Log message severity: Log severity (DEBUG, INFO, WARNING, ERROR, CRITICAL) Returns: Success message or error |
| `google-cloud logging-read-logs` | `{log_filter?: str = "", max_entries?: int = 50}` | Read recent log entries from Cloud Logging Args: log_filter: Optional filter for log entries max_entries: Maximum number of entries to return (default: 50) Returns: Log entries or error message |
| `google-cloud logging-list-logs` | `{}` | List all log names in the project Returns: List of log names or error message |
| `google-cloud logging-delete-log` | `{log_name: str}` | Delete a log Args: log_name: Name of the log to delete Returns: Success message or error |
| `google-cloud logging-create-log-sink` | `{sink_name: str, destination: str, log_filter?: str = ""}` | Create a log sink to export logs to another service Args: sink_name: Name for the sink destination: Destination (e.g., bigquery://project.dataset, storage://bucket-name) log_filter: Optional filter for which logs to export Returns: Success message or error |
| `google-cloud logging-list-log-sinks` | `{}` | List all log sinks in the project Returns: List of log sinks or error message |
| `google-cloud logging-delete-log-sink` | `{sink_name: str}` | Delete a log sink Args: sink_name: Name of the sink to delete Returns: Success message or error |
| `google-cloud logging-export-logs-to-bigquery` | `{dataset_id: str, table_id: str, log_filter?: str = "", days_back?: int = 1}` | Export logs to BigQuery Args: dataset_id: BigQuery dataset ID table_id: BigQuery table ID log_filter: Filter for which logs to export days_back: Number of days back to export (default: 1) Returns: Success message or error |
| `google-cloud logging-create-log-bucket` | `{bucket_id: str, location?: str = "global", retention_days?: int = 30}` | Create a log bucket for storing logs Args: bucket_id: ID for the log bucket location: Location for the bucket (default: global) retention_days: Log retention period in days (default: 30) Returns: Success message or error |
| `google-cloud compute-list-instances` | `{zone?: str = ""}` | List Compute Engine instances Args: zone: Optional zone filter, if empty lists from all zones Returns: List of instances or error message |
| `google-cloud compute-create-instance` | `{instance_name: str, zone: str, machine_type?: str = "e2-micro"}` | Create a new Compute Engine instance Args: instance_name: Name for the new instance zone: Zone where to create the instance machine_type: Machine type (default: e2-micro) Returns: Success message or error |
| `google-cloud compute-delete-instance` | `{instance_name: str, zone: str}` | Delete a Compute Engine instance Args: instance_name: Name of the instance to delete zone: Zone where the instance is located Returns: Success message or error |
| `google-cloud compute-start-instance` | `{instance_name: str, zone: str}` | Start a Compute Engine instance Args: instance_name: Name of the instance to start zone: Zone where the instance is located Returns: Success message or error |
| `google-cloud compute-stop-instance` | `{instance_name: str, zone: str}` | Stop a Compute Engine instance Args: instance_name: Name of the instance to stop zone: Zone where the instance is located Returns: Success message or error |
| `google-cloud compute-restart-instance` | `{instance_name: str, zone: str}` | Restart a Compute Engine instance Args: instance_name: Name of the instance to restart zone: Zone where the instance is located Returns: Success message or error |
| `google-cloud compute-get-instance` | `{instance_name: str, zone: str}` | Get detailed information about a Compute Engine instance Args: instance_name: Name of the instance zone: Zone where the instance is located Returns: Instance information or error message |
| `google-cloud compute-list-zones` | `{}` | List all available Compute Engine zones Returns: List of zones or error message |
| `google-cloud compute-wait-for-operation` | `{operation_name: str, zone: str, timeout_minutes?: int = 5}` | Wait for a Compute Engine operation to complete Args: operation_name: Name of the operation to wait for zone: Zone where the operation is running timeout_minutes: Maximum time to wait in minutes (default: 5) Returns: Operation status or timeout message |

## git

Use `git --help` for Git operations on workspace repositories.

## python3

Execute Python code directly under the agent workspace and return stdout
and stderr. Code can be pasted into a `.py` file and run with `python3`.

Python cannot launch subprocesses or make direct network requests. Run the
documented service commands directly in the shell. Use Python for local
file processing and generating JSON arguments.

name	workspace-commands
description	The shell commands, task tools, and python3 interpreter available in this workspace.

Available commands

Standard Unix commands, among them:

cat  head  tail  ls  find  grep  wc  sort  uniq  cut  tr  sed  awk
diff  tee  xargs  jq  unzip  curl

with pipes, > redirection, $(...) substitution and $'...'.

The task CLIs below are registered with this shell rather than installed as files; do not inspect them with which, file or /usr/bin.

pdf-tools

Use pdf-tools <command> '<JSON arguments>'. Run pdf-tools <command> --help to get more information.

Command	Arguments	Description
`pdf-tools read-pdf-pages`	`{pdf_file_path: str, start_page?: int = 1, end_page?: int = 1}`	Read content from PDF file for specified page range. Supports both local file paths and URLs. For URLs, the PDF will be downloaded to a temporary directory and cached for future use. Note: Avoid reading too many pages at once (recommended: <50 pages) to prevent errors. Args: pdf_file_path: Path to the PDF file or URL to PDF start_page: Starting page number (default: 1) end_page: Ending page number (default: 1) Returns: Extracted text content from the specified pages
`pdf-tools get-pdf-info`	`{pdf_file_path: str}`	Get basic information about a PDF file including page count. Supports both local file paths and URLs. For URLs, the PDF will be downloaded to a temporary directory and cached for future use. Args: pdf_file_path: Path to the PDF file or URL to PDF Returns: Basic information about the PDF file
`pdf-tools merge-pdfs`	`{pdf_paths: list[str], output_path: str}`	Merge multiple PDF files into one. Supports both local file paths and URLs. URLs will be downloaded to temporary files before merging. Mixed local and URL paths are supported. Args: pdf_paths: List of paths to PDF files to merge (in order) - can include URLs output_path: Path where the merged PDF will be saved (must be local path) Returns: Success message with merge details or error message
`pdf-tools extract-pdf-pages`	`{source_path: str, page_numbers: list[int], output_path: str}`	Extract specific pages from a PDF and create a new PDF. Supports URLs for source PDF. The source PDF will be downloaded to a temporary directory if it's a URL. Output path must be a local file path. Args: source_path: Path to the source PDF file or URL to PDF page_numbers: List of page numbers to extract (1-indexed) output_path: Path where the new PDF will be saved (must be local path) Returns: Success message with extraction details or error message
`pdf-tools search-pdf-content`	`{pdf_file_path: str, pattern: str, page_size?: int = 10}`	Search for regex pattern in PDF content and return paginated results. Supports both local file paths and URLs. For URLs, the PDF will be downloaded to a temporary directory and cached for future use. Args: pdf_file_path: Path to the PDF file or URL to PDF pattern: Regular expression pattern to search for page_size: Number of results per page (10-50, default: 10) Returns: Search results with UUID for pagination, or error message
`pdf-tools search-pdf-next-page`	`{search_id: str}`	Get next page of search results. Args: search_id: Search session ID from previous search Returns: Next page of search results or error message
`pdf-tools search-pdf-prev-page`	`{search_id: str}`	Get previous page of search results. Args: search_id: Search session ID from previous search Returns: Previous page of search results or error message
`pdf-tools search-pdf-go-page`	`{search_id: str, page_number: int}`	Go to specific page of search results. Args: search_id: Search session ID from previous search page_number: Page number to go to (1-indexed) Returns: Specified page of search results or error message
`pdf-tools search-pdf-info`	`{search_id: str}`	Get information about a search session. Args: search_id: Search session ID from previous search Returns: Information about the search session

google-cloud

Use google-cloud <command> '<JSON arguments>'. Run google-cloud <command> --help to get more information.

Command	Arguments	Description
`google-cloud bigquery-run-query`	`{query: str, dry_run?: bool = false, max_results?: int = 1000}`	Execute a BigQuery SQL query Args: query: SQL query to execute dry_run: If True, only validate query without running it max_results: Maximum number of results to return (default: 1000) Returns: Query results or error message
`google-cloud bigquery-list-datasets`	`{}`	List all BigQuery datasets in the project Returns: List of datasets or error message
`google-cloud bigquery-create-dataset`	`{dataset_id: str, description?: str = "", location?: str = "US"}`	Create a new BigQuery dataset Args: dataset_id: ID for the new dataset description: Optional description for the dataset location: Dataset location (default: US) Returns: Success message or error
`google-cloud bigquery-get-dataset-info`	`{dataset_id: str}`	Get detailed information about a BigQuery dataset Args: dataset_id: ID of the dataset Returns: Dataset information or error message
`google-cloud bigquery-load-csv-data`	`{dataset_id: str, table_id: str, csv_file_path: str, skip_header?: bool = true, write_mode?: str = "WRITE_TRUNCATE"}`	Load data from CSV file to BigQuery table Args: dataset_id: Dataset ID table_id: Table ID csv_file_path: Path to CSV file skip_header: Whether to skip the first row (header) write_mode: Write mode (WRITE_TRUNCATE, WRITE_APPEND, WRITE_EMPTY) Returns: Success message or error
`google-cloud bigquery-export-table`	`{dataset_id: str, table_id: str, destination_bucket: str, destination_path: str, file_format?: str = "CSV"}`	Export BigQuery table to Cloud Storage Args: dataset_id: Dataset ID table_id: Table ID destination_bucket: Destination bucket name destination_path: Destination path in bucket file_format: Export format (CSV, JSON, AVRO) Returns: Success message or error
`google-cloud bigquery-list-jobs`	`{max_results?: int = 50, state_filter?: str = ""}`	List BigQuery jobs Args: max_results: Maximum number of jobs to return state_filter: Filter by job state (RUNNING, DONE, PENDING) Returns: List of jobs or error message
`google-cloud bigquery-cancel-job`	`{job_id: str}`	Cancel a BigQuery job Args: job_id: ID of the job to cancel Returns: Success message or error
`google-cloud storage-list-buckets`	`{}`	List all Cloud Storage buckets Returns: List of buckets or error message
`google-cloud storage-create-bucket`	`{bucket_name: str, location?: str = "US"}`	Create a new Cloud Storage bucket Args: bucket_name: Name for the new bucket location: Location for the bucket (default: US) Returns: Success message or error
`google-cloud storage-list-objects`	`{bucket_name: str, prefix?: str = ""}`	List objects in a Cloud Storage bucket Args: bucket_name: Name of the bucket prefix: Optional prefix to filter objects Returns: List of objects or error message
`google-cloud storage-upload-file`	`{bucket_name: str, source_file_path: str, destination_blob_name: str}`	Upload a file to Cloud Storage bucket Args: bucket_name: Name of the bucket source_file_path: Local path to the file to upload destination_blob_name: Name for the blob in the bucket Returns: Success message or error
`google-cloud storage-download-file`	`{bucket_name: str, source_blob_name: str, destination_file_path: str}`	Download a file from Cloud Storage bucket Args: bucket_name: Name of the bucket source_blob_name: Name of the blob in the bucket destination_file_path: Local path where to save the file Returns: Success message or error
`google-cloud storage-delete-object`	`{bucket_name: str, blob_name: str}`	Delete an object from Cloud Storage bucket Args: bucket_name: Name of the bucket blob_name: Name of the blob to delete Returns: Success message or error
`google-cloud storage-get-bucket-info`	`{bucket_name: str}`	Get detailed information about a Cloud Storage bucket Args: bucket_name: Name of the bucket Returns: Bucket information or error message
`google-cloud storage-generate-signed-url`	`{bucket_name: str, blob_name: str, expiration_minutes?: int = 60, method?: str = "GET"}`	Generate a signed URL for temporary access to a Cloud Storage object Args: bucket_name: Name of the bucket blob_name: Name of the blob expiration_minutes: URL expiration time in minutes (default: 60) method: HTTP method (GET, PUT, POST, DELETE) Returns: Signed URL or error message
`google-cloud storage-copy-object`	`{source_bucket: str, source_blob: str, dest_bucket: str, dest_blob: str}`	Copy an object between Cloud Storage buckets Args: source_bucket: Source bucket name source_blob: Source blob name dest_bucket: Destination bucket name dest_blob: Destination blob name Returns: Success message or error
`google-cloud storage-move-object`	`{source_bucket: str, source_blob: str, dest_bucket: str, dest_blob: str}`	Move an object between Cloud Storage buckets Args: source_bucket: Source bucket name source_blob: Source blob name dest_bucket: Destination bucket name dest_blob: Destination blob name Returns: Success message or error
`google-cloud storage-enable-versioning`	`{bucket_name: str, enabled?: bool = true}`	Enable or disable versioning for a Cloud Storage bucket Args: bucket_name: Name of the bucket enabled: Whether to enable (True) or disable (False) versioning Returns: Success message or error
`google-cloud storage-get-bucket-size`	`{bucket_name: str}`	Get size statistics for a Cloud Storage bucket Args: bucket_name: Name of the bucket Returns: Bucket size information or error message
`google-cloud storage-set-bucket-lifecycle`	`{bucket_name: str, age_days?: int = 30, action?: str = "Delete"}`	Set lifecycle rules for a Cloud Storage bucket Args: bucket_name: Name of the bucket age_days: Age in days after which to apply the action action: Action to take (Delete, SetStorageClass) Returns: Success message or error
`google-cloud logging-write-log`	`{log_name: str, message: str, severity?: str = "INFO"}`	Write a log entry to Cloud Logging Args: log_name: Name of the log message: Log message severity: Log severity (DEBUG, INFO, WARNING, ERROR, CRITICAL) Returns: Success message or error
`google-cloud logging-read-logs`	`{log_filter?: str = "", max_entries?: int = 50}`	Read recent log entries from Cloud Logging Args: log_filter: Optional filter for log entries max_entries: Maximum number of entries to return (default: 50) Returns: Log entries or error message
`google-cloud logging-list-logs`	`{}`	List all log names in the project Returns: List of log names or error message
`google-cloud logging-delete-log`	`{log_name: str}`	Delete a log Args: log_name: Name of the log to delete Returns: Success message or error
`google-cloud logging-create-log-sink`	`{sink_name: str, destination: str, log_filter?: str = ""}`	Create a log sink to export logs to another service Args: sink_name: Name for the sink destination: Destination (e.g., bigquery://project.dataset, storage://bucket-name) log_filter: Optional filter for which logs to export Returns: Success message or error
`google-cloud logging-list-log-sinks`	`{}`	List all log sinks in the project Returns: List of log sinks or error message
`google-cloud logging-delete-log-sink`	`{sink_name: str}`	Delete a log sink Args: sink_name: Name of the sink to delete Returns: Success message or error
`google-cloud logging-export-logs-to-bigquery`	`{dataset_id: str, table_id: str, log_filter?: str = "", days_back?: int = 1}`	Export logs to BigQuery Args: dataset_id: BigQuery dataset ID table_id: BigQuery table ID log_filter: Filter for which logs to export days_back: Number of days back to export (default: 1) Returns: Success message or error
`google-cloud logging-create-log-bucket`	`{bucket_id: str, location?: str = "global", retention_days?: int = 30}`	Create a log bucket for storing logs Args: bucket_id: ID for the log bucket location: Location for the bucket (default: global) retention_days: Log retention period in days (default: 30) Returns: Success message or error
`google-cloud compute-list-instances`	`{zone?: str = ""}`	List Compute Engine instances Args: zone: Optional zone filter, if empty lists from all zones Returns: List of instances or error message
`google-cloud compute-create-instance`	`{instance_name: str, zone: str, machine_type?: str = "e2-micro"}`	Create a new Compute Engine instance Args: instance_name: Name for the new instance zone: Zone where to create the instance machine_type: Machine type (default: e2-micro) Returns: Success message or error
`google-cloud compute-delete-instance`	`{instance_name: str, zone: str}`	Delete a Compute Engine instance Args: instance_name: Name of the instance to delete zone: Zone where the instance is located Returns: Success message or error
`google-cloud compute-start-instance`	`{instance_name: str, zone: str}`	Start a Compute Engine instance Args: instance_name: Name of the instance to start zone: Zone where the instance is located Returns: Success message or error
`google-cloud compute-stop-instance`	`{instance_name: str, zone: str}`	Stop a Compute Engine instance Args: instance_name: Name of the instance to stop zone: Zone where the instance is located Returns: Success message or error
`google-cloud compute-restart-instance`	`{instance_name: str, zone: str}`	Restart a Compute Engine instance Args: instance_name: Name of the instance to restart zone: Zone where the instance is located Returns: Success message or error
`google-cloud compute-get-instance`	`{instance_name: str, zone: str}`	Get detailed information about a Compute Engine instance Args: instance_name: Name of the instance zone: Zone where the instance is located Returns: Instance information or error message
`google-cloud compute-list-zones`	`{}`	List all available Compute Engine zones Returns: List of zones or error message
`google-cloud compute-wait-for-operation`	`{operation_name: str, zone: str, timeout_minutes?: int = 5}`	Wait for a Compute Engine operation to complete Args: operation_name: Name of the operation to wait for zone: Zone where the operation is running timeout_minutes: Maximum time to wait in minutes (default: 5) Returns: Operation status or timeout message

git

Use git --help for Git operations on workspace repositories.

python3

Execute Python code directly under the agent workspace and return stdout and stderr. Code can be pasted into a .py file and run with python3.

Python cannot launch subprocesses or make direct network requests. Run the documented service commands directly in the shell. Use Python for local file processing and generating JSON arguments.

VFS passed: 5/5
MCP passed: 5/5
Fewer tokens with VFS: 4 of 5 models

Passes and mean tokens per run for each model, VFS vs MCP
Model	VFS	MCP	VFS Tokens	MCP Tokens	Token Reduction Rate
Claude Opus 5.5	1/1	1/1	60.7k	136k	55%
GPT-6.1 Sol	1/1	1/1	32.9k	81.1k	59%
GPT-5.6 Luna	1/1	1/1	39.4k	83.9k	53%
Claude Haiku 5.5	1/1	1/1	490k	530k	8%
Gemini 3.8 Flash	1/1	1/1	470k	448k	−5%