agy_purge

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

With no annotations provided, the description carries the full burden. It discloses the deletion action, the validation constraints (positive integer <= 3650, rejection of zero/negative), and the return value (removed job ids and coarse count). This adds safety context and expected behavior, though it does not detail irreversible effects or permissions.

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 two sentences with no redundancy. The first sentence states the core action, the second provides validation details and rationale. Every word adds value, and the most critical information is front-loaded.

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 description covers the tool's purpose, parameter constraints, and return value, which is sufficient given the simple single-parameter interface and the presence of an output schema. It does not describe the exact structure of the output, but the output schema presumably covers that, and it does not mention edge cases like empty results, but these are minor gaps.

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 only defines `days` as an integer with a default, providing no description. The tool description fills this gap completely by specifying the valid range (1-3650), the requirement for positivity, and the rationale for rejecting zero/negative values, which prevents misuse.

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 action ('Delete') and the resource ('session-store job directories'), and specifies the condition based on mtime and days. It also mentions the return value, which distinguishes it from sibling tools like agy_status or agy_cancel by describing a unique cleanup 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 implies usage for cleaning up old session jobs, and explicitly warns about safe values for `days` to avoid accidental wipes. However, it does not explicitly state when to prefer this tool over alternatives, nor does it mention when not to use it (e.g., if active jobs might be affected).

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