propose_fixes

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

With no annotations, the description carries full burden. It clearly states it is read-only, never writes, and details fix classifications (deterministic, needs-value, manual, infra) and their nature. It lacks auth or rate limit info, but provides substantial behavioral context.

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 front-loaded with key identity ('READ-ONLY safe-fix ADVISOR for ONE page') and each subsequent sentence adds substantive detail. It could be slightly more structured but is efficient without 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 no output schema, the description thoroughly explains what the tool returns: concrete fix proposals with change details, visibility, issue codes cleared, safety notes, and exact edits or classification. It also mentions next steps (preview_fix), making it self-contained.

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%, so baseline is 3. The description adds little to parameter meaning beyond the schema; it mentions 'codes' is optional but does not elaborate on value formats or constraints. However, the fix classification indirectly informs possible values.

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 it is a READ-ONLY safe-fix advisor for ONE page, with a specific verb ('audits', 'proposes') and resource. It distinguishes from siblings by focusing on one page and mentioning preview_fix for dry-run.

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 recommends passing proposals to preview_fix before deciding, and states 'NEVER writes anything' to advise on safe usage. It provides clear context, though lacks explicit when-to-use vs alternatives like audit_site.

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