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

Beyond readOnlyHint=true, the description discloses the status state machine (queued / running with ETA), the polling cadence, the severity sort order, and that re-checks additionally return a diff plus Lighthouse before/after. It is already structured-field-adjacent rather than behavioral in the permission sense, but the status and timing context is genuinely useful.

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 status/result decision, then the payload shape, then the polling instruction. The findings-field enumeration is dense but each clause maps to something the agent will actually consume; no filler sentences.

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?

There is no output schema, so the description carries the return-value burden and does so thoroughly: severity counts, Lighthouse scores, finding ordering and per-finding fields, pagesCrawled, finalUrl, platform, plus the re-check diff. Polling behavior is also covered, leaving no material gap for a single-parameter read tool.

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% and the auditId pattern plus provenance are already documented in the schema, so the description adds little new meaning for the single parameter beyond reinforcing that the ID comes from audit_website or recheck_website. Baseline 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?

States a specific verb (returns status or finished result) and resource (audit), and explicitly ties it to the producing siblings audit_website and recheck_website, so it is distinguishable from them 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 concrete operational guidance: it is the polling endpoint for audits started with audit_website or recheck_website, and instructs polling every 20-30 s while queued or running. It does not address the third sibling scan_website or say when this tool should not be used.

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