prune_executions

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

The description adds significant value beyond the 'destructiveHint' annotation: it states that deletion is permanent and cannot be undone, that it runs as a dry run by default, and that running/waiting executions are never affected. This fully informs the agent of the tool's destructive and cautious behavior.

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 concise (4 sentences) and front-loaded with the core purpose. Every sentence adds necessary information (bulk delete, filters, dry run, permanence, safety for active executions). No redundant or vague statements.

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?

The tool is fairly simple and the description covers key behavioral aspects: dry run, permanence, safety for running executions, and the maximum delete cap is indicated in the schema. Without an output schema, it could mention what is returned (e.g., count), but the description is sufficient for safe usage.

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?

Schema coverage is 100% with clear parameter descriptions. The description adds minimal extra meaning beyond restating the filter concept and highlighting the dryRun default. With full schema coverage, a baseline 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 clearly states the tool's purpose: bulk-delete finished execution records using filters (status, workflow, older than N days) to reclaim database space. The verb 'prune' and resource 'execution records' are specific, and it distinguishes itself from the sibling 'delete_execution' (single) by being a bulk operation.

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?

The description explains the primary use case (reclaim space) and mentions the dry-run default as a safe preview. It also clarifies that running/waiting executions are never touched, implying a safety boundary. However, it doesn't explicitly contrast with other tools like 'delete_execution' for single deletions or provide prerequisites (e.g., permissions).

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