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

Annotations already declare this tool read-only, idempotent, open-world, and non-destructive, so the description does not need to re-state safety. It adds useful behavioral context beyond annotations: the result is a score and each finding is tied to an exact file or tag to fix. It does not mention any network-side crawl activity or rate-limit behavior, but the schema's refresh parameter already communicates the cached/fresh logic.

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?

One tight sentence fully front-loads the tool's purpose and uses a colon-separated list to enumerate the assessment areas plus the actionable output. There is no filler, no repetition of the title, and no unnecessary restating of schema 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?

The tool has no output schema, so the description carries the responsibility of explaining return value intent; it does so by naming the score and the per-finding file/tag fix. It omits the score's scale or output format, but for an agent selecting and invoking the tool with one required domain parameter and an optional refresh flag, the description is sufficiently complete.

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%, with domain documented as the raw user-provided domain (no scheme/path, reserved names refused) and refresh documented as forcing a fresh scan with rate limiting. The description adds no parameter-level detail beyond the generic reference to 'domain'. At full schema coverage, the baseline 3 is appropriate.

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 clearly identifies the tool as producing a discoverability score for a domain and enumerates concrete dimensions: crawl access, site plumbing, page metadata, structured data, and answer-engine readiness. It also promises actionable output, the exact file or tag to fix each finding. It falls just short of a 5 because it is phrased as a noun phrase rather than a direct verb and does not explicitly distinguish itself from the sibling fetch_as_crawler.

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?

The description implies the use case: evaluate and improve a domain's search/AI discoverability, and get concrete fixes. However, it never names alternative sibling tools or states when not to use this tool versus fetch_as_crawler, check_email_security, or verify_fix. Usage guidance is present only by inference from the tool name and topic, not by explicit routing.

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