Audit a live URL for motion accessibility (WCAG 2.2.2 / 2.3.3)

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

Annotations only declare readOnlyHint and openWorldHint; the description carries all the real behavioral weight — fetch limits (12 sheets, 2 MB per response, 8 s timeout), the reduced-motion-safe badge precondition, the not-measurable path, and the review-vs-violation distinction. It also discloses that network I/O occurs, consistent with openWorldHint.

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?

Purpose is front-loaded, then constraints, return shape, and caveats in a logical order, with no filler sentences. It is dense but long, and 'Uses scoring v2. Same engine and scoring as the free site check' is mildly redundant.

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 enumerates the returned fields (ok, url, status, score, findings, groups, summary, badge, coverage) and the error shape with isError:true. Combined with the documented failure and not-measurable modes, an agent has everything needed to call and interpret it.

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?

Only one parameter, and the schema already documents it at 100% coverage as the http/https page URL. The description adds fetch side constraints (sheet count, response size, timeout) that shape expectations but don't add meaning to the url argument itself, so the baseline 3 is appropriate.

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 opens with a specific verb+resource: a static motion-a11y checker that fetches a URL's HTML and linked stylesheets and scans CSS for four enumerated motion issues. It is unmistakable next to non-overlapping siblings (motion_catalog, motion_compile, motion_stats, motion_validate), none of which are URL auditors.

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?

It states clear scope boundaries and exclusions: runtime motion (WAAPI/GSAP/WebGL) is not audited, loading indicators are 'review' not violations, and pages without CSS motion yield status 'not-measurable' with score null. It also tells the agent to read status first. It does not explicitly route to an alternative tool for runtime motion, so it falls short of a full 5.

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