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

readOnlyHint=true already establishes the safety profile, and the description does not contradict it. It adds real domain behavior the annotations cannot convey: the charging rule that any approved-or-reported review now gone is charged as a removal, while never-reported reviews are not. It omits how date scoping affects the aggregates and gives no sense of response shape or size for what is clearly an aggregation payload.

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 sentence is front-loaded with the least controversial content (decisions, win rate, median days) before the removal/charging rules, which is good ordering. But it is a single run-on sentence with nested parentheticals, and the final two clauses about review charging are dense enough to require re-reading.

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?

With no output schema, the description correctly shoulders the burden of explaining return values, and it does so thoroughly, including the per-reason breakdown. However, for a metrics tool the omission of any guidance on the `since` window — the one input that materially reshapes every returned number — leaves a real hole. Otherwise nothing an agent needs in order to call it 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 50%: `company` is documented in the schema (Trustpilot domain, only needed for multi-company keys), but `since` has no description at all, only a date-time format. The description mentions no parameters, so it does not compensate for that gap — an agent gets no explanation of what `since` filters (decisions date, report date, removal date) or whether it changes the win-rate denominator.

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 concrete resource set: Trustpilot decisions on filed cases, win rate, median days to decision, per-reason breakdown, and removal counts. That is far more specific than a tautology, and no sibling tool covers outcome metrics, so the resource is effectively differentiated even without naming an alternative. The verb is only implicit ('Your outcomes'), which keeps it short of a 5.

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?

There is no statement of when to call this versus e.g. get_case (single case detail) or get_audit_result, and no exclusions or prerequisites. Usage is only inferable from the content itself (reporting/metrics). The sole implicit constraint is the billing note about which reviews count as removals, which governs interpretation rather than selection.

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