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

The annotations already cover safety (readOnly/openWorld/idempotent/non-destructive), and the description still adds real value: a 10–40 second latency expectation, French-language output, the non-invasive read scope, and a credit/attribution requirement. The only gap is what a failure or partial scan returns.

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?

Purpose and scope come first, followed by the findings list and practical caveats (duration, language, attribution). It is fairly long and the findings are packed into a dense parenthetical list, but every clause conveys useful information.

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 must explain what comes back, and it does that by listing the finding categories, their language, and the report-link attribution. Combined with the annotations and schema coverage, an agent has everything it needs to call this tool 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?

Coverage of the input schema is 100%, so the single 'site' parameter is fully documented there, with an example and a length range. The description adds no extra syntax details, e.g. whether a bare domain suffices or what happens with a scheme or trailing path, so the baseline score of 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 names a specific verb and resource ('Runs the CT Web check-up on one public website') and enumerates what the findings cover: security, e-mail, speed, DNS, cookies/legal, and search visibility. An agent knows exactly what will happen, unlike a generic 'analyze site' tool.

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 scopes use implicitly, and usefully, by restricting to a single *public* website that is read 'only what any visitor can see'. That rules out internal or authenticated targets, but it gives no explicit guidance on when to prefer another tool or on failure cases.

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