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

Beyond the readOnly/idempotent annotations, it discloses a key behavioral boundary ('this tool never starts one' – i.e., it never triggers a crawl) and defines the error sentinel 'no_site_snapshot'. It also spells out the exact return payload, which the annotations alone do not 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?

Two sentences, both dense and front-loaded: the first delivers the payload contents, the second handles routing and the error case. There is no filler or repeated structured data.

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 burden of describing returns, and it does so thoroughly (score categories, measurement state, page counts, top-10 issue structure). For a two-parameter read tool with safety annotations, nothing material 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?

Schema coverage is 100% and both parameters are fully documented in the schema, including the 'omit for latest crawl' default and the crawl-id alias. The description's phrase 'or a chosen snapshot' restates that without adding syntax or format detail, 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?

The description uses a specific verb and resource ('Read the Site Health summary of the latest crawl, or a chosen snapshot') and enumerates the returned fields (fundamentals/AI-readiness scores, measurement state, page counts, top 10 issues with rule_id, severity, remediation). It also differentiates itself from siblings by naming read_site_pages, read_ai_crawlability, and render_site_health with their distinct roles.

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 explicitly states the usage context ('latest crawl, or a chosen snapshot'), gives a negative case ('unavailable no_site_snapshot means no crawl was analyzed yet'), and routes the agent to alternatives: read_site_pages with a rule_id for affected pages, read_ai_crawlability for robots access, render_site_health for the interactive view.

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