a11y_autofix

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

No annotations exist, so the description carries the full burden, and it does well: deterministic behavior, a closed fix list, explicit non-goals, and the return shape (fixed_html + aplicados + no_aplicados). It omits idempotency/auth details, but for a pure HTML-string transform those are minor.

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?

Front-loads the core purpose, but the single dense paragraph contains marketing noise ('the honest anti-overlay') and mixed Spanish identifiers that reduce scannability. Trimmed, it would be sharper.

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?

There is no output schema, so the description compensates by naming the return keys and the no_aplicados reason/remediation behavior. Combined with the 100%-covered input schema, an agent has what it needs to invoke and interpret the 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 description coverage is 100%, so baseline is 3. The description restates the schema conditions ('fill missing html lang and empty title when provided'), adding only marginal meaning beyond the schema's own conditional wording.

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+resource ('deterministic safe auto-fixes applied to HTML') and enumerates the closed list of fixes, which clearly differentiates it from the surrounding a11y audit/suggestion siblings. An agent can tell this is a fixer, not an auditor, without opening the schema.

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 gives the when-not boundary: 'Everything requiring judgment (alt text, contrast, accessible names) is NOT touched' and routes those cases to no_aplicados with remediation. It does not name a specific sibling alternative, but the exclusions are clear enough to select correctly.

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