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

Adds substantial context beyond the annotations: no third-party API, robots.txt-awareness, same-origin scoping, background execution, and honest flagging of blocked pages. This is precisely the operational detail the openWorldHint/readOnlyHint annotations cannot convey.

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?

A single dense but well-organized paragraph that front-loads the action and then the follow-up flow. Every clause is informative, though the sentence is lengthy and could be split for faster scanning.

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?

An output schema exists, so return values need no explanation; the description instead covers the async lifecycle and the follow-up tools, which is exactly what an agent needs to invoke and complete this workflow 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 description coverage is 100%, so the schema already documents url, maxPages, projectId, and runLighthouse. The description reinforces the crawler's scope (robots.txt-aware, same-origin) and the Lighthouse sampling, but adds little parameter syntax or format detail beyond the schema baseline.

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 (start/run) and resource (site audit) and details exactly what the crawl checks: broken links, titles, redirect chains, orphan pages, canonical issues, thin content. It clearly distinguishes itself from siblings by routing results through get_audit_status and get_audit_issues.

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?

Explicitly describes the workflow: it runs in the background, so the agent must poll get_audit_status and then read get_audit_issues. It also notes the optional Lighthouse step. It does not clarify when to prefer this over the semantically adjacent sibling inspect_urls, so it stops short of full when/when-not coverage.

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