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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real value beyond them: long-poll semantics, a 0–25 second ceiling on `wait`, the fact that an expired wait returns `status: running`, and the instruction to repeat. It does not detail response structure or rate limits.

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?

Three sentences, but the long-poll behavior is stated twice in near-identical wording ('answers as soon as a running test finishes' repeated). The repetition wastes space, though the rest is front-loaded and free of padding.

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 does carry the burden of describing returns and it names the statuses and payload (scores, metrics, biggest savings, failed, running). It is nearly complete for a polling read tool; only the exact response shape and error/failure conditions are left implicit.

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 67% and the schema's `wait` entry only says 'seconds to wait, 0–25'. The description clarifies what that wait actually does (returns as soon as a running test finishes, or after `wait` seconds with `status: running`), adding meaning not present in the schema.

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?

States the resource (lab test results of an audit, mobile and desktop) and the possible states (running, finished with scores/metrics/savings, failed). It never uses an explicit retrieval verb and doesn't distinguish itself from the similarly named sibling `lab_test`, but the resource and outcome set are clear.

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?

Provides concrete polling mechanics (use `wait`, repeat until it is not running), which is useful operational guidance, but never says when to choose this over `lab_test` or `get_audit`, and gives no prerequisites beyond the implied guest_token.

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