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

Annotations already cover the safety profile (readOnly, idempotent, openWorld), yet the description adds genuinely new behavioral facts: the 10-25 second runtime, the daily-per-client rate limit, and the important gating detail that failure/warning specifics and platform fixes are locked until a work email is used via unlock_report. That locked-vs-unlocked split is exactly the kind of context an agent cannot infer from annotations or schema.

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?

The first sentence front-loads the action and the full return payload, and the remaining sentences each carry distinct, non-redundant information (unlock path, latency, input constraint, rate limit). It is somewhat run-on with several clauses packed into the opening sentence, which keeps it just short of ideal.

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 describe returns, and it does so thoroughly (score, grade, platform, category scores, top three issues, all 48 check statuses, shareable link). Combined with the latency note, the rate limit, the email-gated unlock path, and the URL constraint, an agent has everything needed to call it and set expectations.

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 the single 'url' parameter is already documented, so the structured data carries the load (baseline 3). The description still adds constraint meaning beyond the schema by specifying that a deep link is invalid and only a domain or homepage URL is acceptable.

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?

Names a specific verb and resource ('Runs the free ROAS Expert audit on a public website') and enumerates the concrete output surface: score out of 100, grade, detected platform, category scores, top three issues, status of all 48 checks, and a report link. It also points at the sibling boundary by stating that per-check detail and fixes are 'unlocked ... through unlock_report', so an agent can distinguish it from unlock_report/explain_fix/get_report without opening any schema.

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?

Gives clear invocation context ('Use the domain or homepage URL, not a deep link') and a stated operational limit ('Free plan: a few audits per day per client'), plus it routes the user to unlock_report for deeper detail. It does not explicitly state when to prefer get_report, list_checks, or explain_fix instead, so it falls short of full when/when-not guidance.

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