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 tool's behavior: identifies failure modes, returns fixed code, and indicates rate limits. It does not mention side effects or persistence, but for a code-fixing tool, this is adequate.

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 concise (6 sentences) and front-loaded with core purpose. Every sentence provides necessary information: what it does, how it works, output, limitations, and alternative. No fluff.

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 simplicity of a single-parameter tool with no output schema, the description covers the essential aspects: input, output format, and usage limits. It is missing edge cases (e.g., non-broken code) but overall complete for typical use.

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 description coverage, the baseline is 3. The parameter description adds no new meaning beyond the schema, but is clear and consistent with the tool purpose. The tool description itself adds high-level context, but for the parameter specifically, it's adequate.

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 that the tool diagnoses and fixes broken AI-generated code, listing specific failure modes and output format. It distinguishes itself from the sibling tool 'provibe_audit' for full repo audits.

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 mentions a usage limit (3 free per 24h) and provides an alternative tool for full repo audits, giving clear context for when to use this tool vs. another. It lacks explicit exclusions but is sufficient.

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