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

With no annotations, the description carries the full burden and does well: it discloses no new audit is started, no charge is incurred, no checks are invented, and that an empty group means zero findings rather than a clean bill of health. It omits polling cadence/rate limits and error states, keeping it short of a 5.

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?

Front-loads the purpose and required argument, then stacks short, high-signal clauses. The choppy 'Does NOT...' repetitions are slightly verbose but each carries a distinct constraint, so little is wasted.

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 and no annotations, the description supplies the return shape (findings grouped as priority / worth considering / not measured) plus the empty-group caveat, which is what an agent needs to interpret results. Error handling and the undocumented audit_id are the remaining gaps.

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%: job_id is documented in the schema as coming from audit_page and the description reinforces 'Pass the job_id'. The second parameter audit_id is left entirely unexplained in both schema and description, so the description only marginally compensates.

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 a specific verb and resource ('Poll an audit'), names the originating sibling (audit_page) and explicitly negates the confusing alternative ('Does NOT start a new audit'). An agent can immediately tell it apart from audit_page or check_vitals.

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 the exact calling protocol: it must follow audit_page, requires job_id, and should be re-invoked while status is running. It also names the alternative behavior it does not perform, so the when/when-not split is explicit.

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