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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, so the safe-read profile is covered. The description adds real behavioral context beyond that: the long-poll contract, the 15-second ceiling, and the fact that a timed-out response returns status running so the caller must re-poll. It does not describe the guest_token authorization requirement beyond what the schema says, nor response shape, so this is solid but not rich.

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 core idea is clear, but the long-poll behavior is stated twice in near-identical sentences ('With wait (up to 15) it answers as soon as a running test finishes' then 'Long-poll: with wait the answer comes as soon as a running test finishes'), wasting a full sentence. The lead clause is also a fragment that omits any verb.

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 carries the burden of describing returns, and it does: it enumerates the statuses and names the payload fields (scores, metrics, biggest savings). Combined with the polling guidance, an agent has enough to call it correctly; only the sibling relationship and auth expectations remain thin.

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%, so the baseline is 3. The description explains the wait parameter's role in the polling loop rather than its units or range, largely repeating the schema's own wording ('0–15', 'as soon as a running test finishes'), and says nothing extra about id or guest_token.

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 identifies the resource concretely: the lab tests belonging to an audit, covering both mobile and desktop, with the three possible states (running, finished with scores/metrics/savings, failed). That is more than a restatement of the name, and an agent can tell what data it returns. It does not, however, differentiate itself from the sibling lab_test, and the retrieval verb is only implied by the noun phrase.

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 guidance exists only for the polling pattern: pass wait (up to 15s) and repeat until the status is no longer running. That is genuinely actionable, but the description never says when to choose this tool over lab_test, audit_site, or audit_url, and gives no exclusion for the non-polling case.

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