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

Annotations only declare readOnly and openWorld; the description adds substantial behavioral content beyond them: the three verdict values (clear, review, flagged), that findings are reported per skill folder with file, line and matched text, and that non-directory skills are fetched and scanned live. This is exactly the extra context annotations cannot convey.

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?

Four short sentences, front-loaded with the purpose, then input forms, then return shape and the live-fetch caveat. No filler; every clause carries information an agent needs.

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?

With no output schema, the description takes on the return-value burden and does so: verdict categories plus per-finding file/line/text. Combined with accepted input forms and the live-scan note, nothing material is missing for a one-parameter tool.

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% and the schema already documents the slug-or-URL format, so baseline is 3. The description still adds real meaning by enumerating accepted URL granularities — repository root, a folder inside one, or a SKILL.md file — which the schema's single example does not make explicit.

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?

States a specific verb and resource ('Safety-check a skill') and bounds it to the pre-install decision. It is clearly distinguishable from siblings like get_skill (retrieval) and search_skills (discovery), which are referenced as sources rather than duplicates.

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?

Gives a clear usage context ('before installing it') and names the two accepted input routes, pointing at search_skills for slugs. It stops short of saying when to prefer this over get_skill or get_proof, but the pre-install framing is explicit enough to route an agent.

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