gc

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

No annotations are provided, so the description carries full burden. It discloses the destructive potential by mentioning dry_run safety, and the threshold criteria. However, it does not detail side effects, irreversibility, or behavior during actual deletion.

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 sentence that is front-loaded with the main purpose. No extraneous words, every part earns its place.

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?

No output schema is provided, and the description does not explain return values or behavior. It lacks context on what happens after the call (e.g., list of deleted items, effect on other tools). It is complete enough for a simple tool but leaves 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?

Schema description coverage is 100%, baseline set to 3. The description only reiterates the dry_run default and does not add additional context or relationships between parameters beyond what the schema already provides.

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 verb 'Garbage collect' and resource 'stale memories below retention threshold'. It is specific and distinct from many siblings, but does not explicitly differentiate itself from other memory management tools like 'consolidate' or 'merge_candidates'.

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 garbage collection with a safe default (dry_run=true), but provides no explicit guidance on when to use this tool versus alternatives, nor any conditions that would make it inappropriate.

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