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

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing that execution is asynchronous, returns a new auditId to poll with get_audit, and is rate-limited (free: 2 audits per IP per 24 h). It also describes the downstream diff output categories (fixed / still open / new / unverified, Lighthouse before → after), which no annotation or output schema provides.

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 the tool does, followed by when to call it and then the operational caveats (async, quota). No filler and nothing repeated from the schema.

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 compensates by explaining way the results arrive (a new auditId polled via get_audit) and what the diff contains. Async behavior, quota, and linkage to the prior audit are all covered, so an agent has everything needed to call it correctly.

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 100%, so the baseline is 3, but the description adds real meaning: auditId must reference a finished audit whose URL and page count are inherited by the re-run. That tells the agent more about the parameter's effect than the schema pattern/description alone.

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 action (re-run the same audit with the same URL and page count) plus the key mechanic: it links to the original auditId so get_audit produces a diff. This clearly separates it from audit_website (fresh audit) and get_audit (polling/results) without the agent needing to open a 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 an explicit trigger: 'Call it after you have deployed fixes.' Combined with 'linked to the original auditId' and the audit_website comparison, the agent can infer the alternative for a first-time audit. It stops short of an explicit when-not-to-use statement (e.g., don't use before fixes are deployed or without a completed auditId).

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