a11y_criterion

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

No annotations are supplied, so the description carries the burden, and it does well: it discloses the return shape (requirement, typical failures, verification, tool-to-criterion mapping) and the bilingual es/en behavior. It does not state that it is read-only or offline/lookup-based, but nothing about it is misleading.

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?

Three sentences, front-loaded with what it does and ending with the when-to-use rule. The inline code examples are slightly redundant but cheap and genuinely reduce ambiguity about the input format.

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?

With no output schema and no annotations, the description must carry the return-value burden and it does, enumerating what the explanation contains. Minor gap: no hint about failure behavior for an invalid code or whether codes map to WCAG 2.1 vs 2.2.

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 50% (only 'code' documented). The description compensates by giving concrete code formats ('1.4.3', '2.5.8', '4.1.2') and the es/en language pair, effectively documenting the undocumented lang parameter's purpose.

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 ('Explains') and resource ('a WCAG 2.2 success criterion') with contents spelled out: requirements, typical failures, and verification mapping. This clearly separates it from the audit/contrast/autofix siblings, which measure or mutate rather than explain.

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?

Gives explicit trigger conditions: 'Use it whenever you need to explain WHY a finding matters or what the criterion actually says.' That is a clear usage context, though it does not name a specific sibling alternative to prefer for the lookup-adjacent case.

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