analyze_accessibility

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

Annotations only cover the read-only/open-world profile; the description adds substantial context beyond them: sampling caps, exclusion of opacity-group samples counted in coverage.skippedOpacityGroups, uncomposited backgrounds/gradients/pseudo-elements, heuristic:true, graceful degradation to {error}, and a licensing restriction. This is exactly the extra behavioral layer the schema does not carry.

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-loaded with the core framing and limitation caveat before the feature list; nearly every clause carries information. It is dense as a single run-on paragraph, which costs a point on structure but not much on content value.

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, the description does the work of naming the result shape (coverage, skippedOpacityGroups, heuristic:true) and explicitly lists the checks performed (alt coverage, heading ladder, tabindex/outline rules, unlabeled controls, lang/title). An agent knows both what goes in and roughly what comes back.

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 all three parameters are already documented. The description restates the limit default and max but adds no semantics beyond the schema, and it never mentions the viewport parameter or what mobile vs desktop sampling implies.

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?

Names a specific verb and resource ('collect accessibility EVIDENCE from a live page') and immediately draws a sharp boundary against a WCAG pass/fail audit, so an agent can tell it apart from sibling audit_url without opening either 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?

Gives clear context for when to use it (evidence gathering on a live http(s) page, needs the playwright dependency) and explicitly frames what it is not ('not a WCAG pass/fail grade'). However, it never names the alternative tool to use for a pass/fail verdict, leaving that routing to inference.

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