cleanup_garbage

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

With no annotations, the description must disclose behavior. It explains the dual mode of operation (list vs. apply) and the 'everything' shortcut. It also mentions the return format. The description implies destructive capability with 'apply=True to actually remove,' which is sufficient transparency. No hidden behaviors are apparent, though it could explicitly warn about irreversibility.

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 very concise (5 lines), with clear sections: purpose, usage guidance, and return format. Every sentence adds value with no redundancy or fluff. It is well-structured and 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 tool has 8 parameters and no annotations, but does have an output schema. The description covers the overall purpose, common usage patterns, and return format. However, it misses details on several parameters (e.g., retention settings) and does not explain how they interact. This could lead to suboptimal use by an AI agent, but the main functionality is clear enough for basic tasks.

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 0%, so description must compensate. It explains the 'everything' and 'apply' parameters and mentions the categories (bundles, debug logs, artifacts). However, it does not explain parameters like 'keep_bundles', 'debug_older_than_days', 'keep_artifacts', or the other booleans. Only partial coverage is provided, which is minimally adequate but incomplete.

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: garbage-collecting accumulated research-hub files, with a specific verb ('Garbage-collect') and resource. It also explains the default behavior (listing candidates) and the version requirement. However, it does not differentiate from sibling tools like 'tidy_vault', which may have overlapping functionality.

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 explicitly provides usage triggers: 'Use when: user says "clean up", "free disk space", or "GC the vault".' It also explains the difference between default (dry-run) and apply mode, giving clear guidance on when to pass parameters. However, it does not mention scenarios where this tool should not be used.

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