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

With no annotations, the description carries the full load and does well: it discloses the cost (2 credits per call), that results include a 0-100 score and severity-ranked issues with exact fixes, and that link checking is capped at 25. It omits auth/permission requirements and does not explicitly confirm the operation is read-only.

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 tight sentences, front-loaded with purpose and followed by return shape and cost. Nothing is redundant or filler.

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?

No output schema exists, and the description compensates well by describing the return payload (score, severity-ranked issues, fixes) and cost. The key gap is that no parameter is required and the mutual exclusivity of url versus site_id+path is never explained, leaving the agent to guess which targeting mode to use.

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 75%, so url/path/site_id are largely documented in-schema, but the description adds a constraint the schema lacks: check_links examines 'up to 25 links on the page,' and it notes the public-vs-hosted target choice. It does not explain the url vs path+site_id relationship.

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?

Specific verb (check/audit) plus resource (public web page or hosted site) with the audited dimensions enumerated (SEO, accessibility, mobile, performance, security). It implicitly differentiates from site_autofix by promising to 'list fixes' rather than apply them, though no sibling is named explicitly.

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 clarifies the two input contexts (any public page vs one of your hosted sites), which implies when it applies, but never states when to prefer site_autofix, crawl_site, check_urls, or security_headers, and gives no exclusions or prerequisites.

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