vertex-mcp-server

by app.run.us-central1.vertex-mcp-server-1069561025565

run_data_driven_optimize

Starts a data-driven prompt optimization job on Vertex AI.

    This method uses a dataset and configurable metrics. The `config_gcs_path`
    must point to a JSON file in Google Cloud Storage.

    Args:
      config_gcs_path: The Google Cloud Storage URI (e.g.,
        "gs://your-bucket/config.json") to a JSON file containing the Prompt
        Optimizer configuration. This is required.
      service_account: The service account email to run the job. This is
        required.
      prompt_optimizer_method: The method for prompt optimization. Either
        'VAPO' or 'OPTIMIZATION_TARGET_GEMINI_NANO'.
      wait_for_completion: If True, the tool will block until the Vertex AI
        CustomJob completes. Defaults to False.

    Returns:
      A string indicating the status and details of the optimization job,
      including a link to the Vertex AI console.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`config_gcs_path`	Yes
`service_account`	Yes
`wait_for_completion`	No
`prompt_optimizer_method`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description carries the burden and does well by disclosing the blocking behavior via wait_for_completion parameter and the format of config_gcs_path. However, it does not mention other behavioral aspects like potential costs, quota usage, or error conditions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections (Args, Returns) but is slightly verbose for a tool description. It could be more concise by removing docstring conventions like 'Args:' and integrating parameter details into flowing prose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema exists, the description appropriately focuses on input parameters. It covers all key aspects of invocation: required parameters, format of config file, method options, and waiting behavior. However, it lacks context on prerequisites like IAM permissions or job lifecycle expectations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description provides detailed meaning for all four parameters beyond the input schema. For each parameter, it explains the type, required status, and acceptable values (e.g., prompt_optimizer_method options are explicitly listed). This fully compensates for the 0% schema description coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool starts a data-driven prompt optimization job on Vertex AI, specifying the resource and action. It distinguishes from sibling tools like analyze_data_driven_optimize_results and write_data_driven_optimize_config by focusing on job initiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains what the tool does and mentions required parameters and config file location, but does not provide explicit guidance on when to use this tool versus alternatives like analyze_data_driven_optimize_results or write_data_driven_optimize_config. No 'when not to use' information is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All vertex-mcp-server tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.1/5.0

Disambiguation4/5

Tools are generally distinct, with prompt CRUD operations clearly separated from optimization workflows. However, 'analyze_data_driven_optimize_results' and 'generate_html_report' could be confused as both relate to results analysis, and 'call_dashscope_mcp' is an outlier with a different purpose.

Naming Consistency5/5

All tools follow a consistent snake_case verb_noun pattern (e.g., create_prompt, run_data_driven_optimize, write_data_driven_optimize_config). The naming is predictable and clear, with no mixed conventions.

Tool Count5/5

11 tools is appropriate for a Vertex AI prompt optimization and management server. It covers prompt CRUD, optimization jobs, config generation, analysis, and reporting without being excessive or insufficient.

Completeness4/5

The tool surface covers prompt lifecycle (CRUD) and key optimization workflows (data-driven, few-shot, config, analysis, report). Minor gaps exist, such as no dedicated tool to fetch optimization job status separately (though wait_for_completion is an option), and 'call_dashscope_mcp' feels extraneous.

Resources

Need Help?