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

Annotations already cover the safety profile (readOnly, idempotent, openWorld), and the description adds genuinely useful context beyond them: the exact breadth (30 checks in five named groups), the latency ('takes 10 to 30 seconds'), and the shape of the result. That latency disclosure is exactly the kind of operational detail 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?

Three sentences, front-loaded with what is scored, then the breakdown of checks, then what comes back and how long it takes. No filler, no repetition of the title, and the most decision-relevant facts (breadth, output, latency) lead.

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, yet the description fully characterizes the return value — score out of 100, grade, per-group scores, and every problem with its point cost — plus runtime. For a single-parameter read-only audit tool, an agent has everything needed to call it and interpret the result.

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% and there is only one required parameter, so the schema already explains the domain format and that a full URL is accepted with only the hostname used. The description adds no parameter-level detail, which matches the baseline 3 for schema-covered inputs.

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 and resource: 'Scores how well AI search engines ... can find, read and understand a website', naming the four engines and the five check groups. The scope is unmistakable, but it never names or contrasts with the sibling check_ai_crawlers, even though 'AI crawler access' is listed as one of its own groups — the agent must infer that relationship.

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?

Usage is implied: run this for a full AI-visibility audit of a site, since it bundles 30 checks across five areas. There is no explicit when-to-use vs. when-not-to-use, and no routing to check_ai_crawlers for a narrower crawler-only check, so the agent is left to infer which of the two tools to pick.

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