Check a page's accessibility

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

Annotations already mark it read-only and non-destructive, and the description adds a substantial amount beyond that: it does not run JavaScript or compute CSS, it is deterministic, and every issue includes a WCAG reference, severity, snippet, and fix. This is especially valuable because there is no output schema to document the return shape.

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 definition is front-loaded with the core action and then lists the checks and limitations in one dense paragraph. The exhaustive rule list and issue-format details all earn their place, though the single paragraph could be more scannable with bullets or separation between purpose, checks, output, and limitations.

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?

For a tool with no output schema and a complex rule set, the description is complete: it covers what it checks, what each issue contains, what it cannot do, and how it relates to preview URLs and browser audits. An agent has enough context to invoke it correctly and interpret results.

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 the schema already documents all five parameters, including preview-token and rules semantics. The description does not add parameter-level meaning beyond what the schema provides, but it does not need to; the baseline of 3 applies.

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 and resource: 'Fetch a page on the configured site and run deterministic accessibility checks on its server-rendered HTML.' It enumerates the exact rule set and explicitly positions the tool as a complement to browser audits, so an agent can distinguish it from generic audit or validation tools.

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 gives clear context for when to use the tool: server-rendered HTML, draft-theme preview URLs from get_preview_url, and situations where a full browser audit is unnecessary or out of scope. It does not, however, explicitly name sibling alternatives or state 'use this instead of X', so it stops short of full when-to-use/when-not-to-use guidance.

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