audit_url

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

Annotations indicate it's not read-only (runs audit), not destructive, not idempotent. Description adds that offline mode is static-only, which is a behavioral constraint. It doesn't discuss rate limits or side effects beyond the audit computation. No contradiction with annotations.

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 one sentence with a short follow-up note. It is front-loaded with the purpose and uses concise language. Every sentence adds 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?

Given 7 parameters and output schema exists, the description covers the essential: what the tool does, output format (top 5 issues + scores), and a special mode caveat. It references a sibling for more details. It doesn't explain 'static-only' further, but with output schema present, it is fairly complete.

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 baseline is 3. The description adds context about offline mode for localhost/file:// URLs, which adds meaning to the offline parameter. However, it doesn't elaborate on other parameters like timeout, wait, baseline_id, etc. The additional value beyond schema is marginal.

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 runs a full UX and accessibility audit on a live URL, returns the top 5 issues and scores, and distinguishes from get_findings for the full list. It also notes offline mode limitations.

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 explicitly tells when to use this tool (to get top issues) and when to use get_findings (for full list). It also mentions offline mode suitability for local HTML/Storybook. Could be slightly more explicit about when not to use, but it's clear enough.

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