jobs_purge

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

No annotations are provided, so the description bears full responsibility. It discloses that active runners are terminated, which is valuable. However, it does not mention irreversibility, required permissions, or potential impacts on other resources. More detail would be beneficial.

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

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

The description is a single, well-structured sentence. It communicates the core action and a key behavioral detail without any fluff or repetition. Highly efficient.

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

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

Given the simplicity of the tool (one parameter, no output schema), the description is fairly complete. However, it lacks information about return values, error handling, or any prerequisites. For a destructive action, more context would improve completeness.

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

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

The schema has 100% coverage for the single parameter project_id with a description 'The project ID'. The tool description adds no additional semantic meaning beyond what the schema already provides. Baseline score of 3 is appropriate.

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

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

The description uses specific verb 'purge', identifies the resource 'managed job runs', and scopes it to 'for a project'. It also mentions a unique behavioral aspect: 'terminating known active runners first'. This clearly distinguishes it from sibling tools like jobs_cancel or jobs_submit.

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

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

While the description implies this tool is for bulk cleanup of job runs, it does not explicitly state when to use this tool over alternatives like jobs_cancel. There is no mention of prerequisites, limitations, or exclusions. The guidance is minimal.

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