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

Goes well beyond the readOnlyHint/openWorldHint annotations: it names known limitations (contrast not measured, English-only Flesch, homepage-only broken-link check capped at 25 links), documents typed failure reasons (blocked_403, not_found, timeout), and states the return shape is a list of concrete issues.

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-loads purpose before the long enumeration of checks, and every listed item is a real signal the tool measures. The middle checklist is dense but earns its space; only slight trimming would be possible.

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 one simple parameter and no output schema, the description still covers return shape ('list of concrete issues'), failure modes, and scope boundaries. Nothing material for correct invocation is missing.

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?

Only one parameter (url) and the schema already documents it at 100% coverage with an example format. The description implies a single full page URL but adds no syntax or constraint detail beyond the schema, so 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 and resource ('Fetch a page and audit core on-page SEO signals') and enumerates the audited signals precisely. The closing sentence 'Single page only — not a site crawl' explicitly separates it from crawl-oriented siblings.

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 scopes usage with 'Single page only — not a site crawl,' which tells the agent when not to use it. It does not name which sibling to use for a full crawl (e.g., ai_crawler_audit), leaving that inference to the caller.

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