audit_pa11y

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

No annotations are provided, so the description must carry the burden of behavioral disclosure. It states the engine and input options but does not describe what happens during the audit (e.g., whether it is read-only, if it modifies state, or what the triggering behavior is). The return format is covered by the output schema, but internal behavior is opaque.

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 two sentences, front-loaded with the core action, and includes key constraints. No superfluous information.

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 4 parameters with 0% schema coverage and no annotations, the description covers the input requirements and a prerequisite. It misses explaining the 'level' parameter and does not provide usage examples, but the output schema is present, reducing the need for return value details.

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 0%, so the description must compensate. It adds that url, html, and session_id are mutually exclusive and one is required, which is not apparent from the schema (all optional). However, it does not explain the 'level' parameter or defaults. This adds meaningful context but leaves gaps.

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 tool audits with the pa11y engine, specifying it uses HTML_CodeSniffer and axe runners. This distinguishes it from sibling tools like audit_axe (which likely uses axe only) and audit_lighthouse (Lighthouse engine).

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 tells the user that one of url, html, or session_id must be provided, but does not explicitly compare with similar audit tools (e.g., audit_axe, audit_ibm) to guide selection between engines. Usage context is implied rather than explicit.

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