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

The description states it applies fixes via save_skill, which is a write operation, but annotations declare readOnlyHint=true. This direct contradiction severely misleads the agent about the tool's side effects.

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 thorough and front-loaded with the core purpose, but slightly verbose in detailing the audit process. Every sentence is informative, but some redundancy exists.

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 complexity and presence of an output schema, the description provides a complete picture of inputs, process, and outputs. However, the contradiction with annotations undermines trust and 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?

With 100% schema coverage, the description adds significant value by explaining the two modes, the optional nature of skill_id, and the interactive local file audit, far exceeding the schema's brief description.

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 reviews a skill against best practices and fixes flags, with specific verbs 'Review' and 'fix'. It distinguishes between auditing a hosted skill (via skill_id) and a local file, differentiating it from sibling tools like get_skill or save_skill.

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 two usage modes (with or without skill_id) and implies when to use each. It references related tools (run_verifier, save_skill) but does not explicitly list when not to use or compare to alternatives like optimize_skill.

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