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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false. The description reinforces these and adds important behavioral details: errors never raise protocol errors but return an error object with remediation advice. This adds value beyond annotations and discloses error handling behavior. Could be slightly higher if it mentioned rate limits or quota, but it's solid.

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 well-structured: purpose first, then checks, then input/output example, then usage guidance, then error handling. It front-loads key information. While relatively long, every sentence adds value and flows logically. A minor trim could improve conciseness, but it is efficient for the information density.

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 simple schema (1 param), rich annotations (readOnly, idempotent), existence of an output schema, and sibling tool list, the description covers all necessary aspects: purpose, input format, output verdict/findings, error handling, usage boundaries, and safety profiles. No gaps remain for an agent to misunderstand.

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%, so baseline is 3. The description adds an example JSON input ({"content": "<text>"}) which clarifies the expected format and typical usage. This provides concrete context beyond the schema's text description. No excess; adds meaning.

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 'Audit' and the resource 'agent skill or instruction file'. It specifies what it checks (governance smells like prompt injection, guardrail bypass, etc.) and distinguishes itself from sibling 'injection_scan' by noting it is for pre-trust auditing, not runtime input. Very specific and differentiated.

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?

Explicitly says 'Use before trusting a skill or instruction file that came from outside your own repository' and 'Not for arbitrary untrusted input at run time (injection_scan)'. This provides clear when-to-use and when-not-to-use guidance, including naming the alternative tool.

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