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

Annotations only declare readOnlyHint=true and destructiveHint=false; the description carries far more behavioral detail. It discloses the progress field when available, the failure_reason_code enum, failure_next_step, the absence of both on cancelled runs, and the exact relationship of health_score and issues_found to get_report's summary. This goes well beyond the annotations without contradicting them.

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 description is long but every sentence earns its place: the purpose is front-loaded, then status branches are laid out in reading order, and nuanced edge cases like cancelled vs failed and null health_score are explained with concrete field names. It is dense rather than padded.

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 full burden of explaining the response contract. It covers the status states, polling behavior, progress field, error fields, failure reason code enum, next-step guidance, and derived health fields. An agent has enough context to poll correctly, recognize terminal states, and decide whether to call get_report.

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?

The input schema already covers run_id completely at 100% coverage, including its origin from run_audit or list_audits. The description repeats this origin but adds no new parameter-level semantics such as format, length, or validation constraints, so it stays at the baseline for fully documented schemas.

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 opens with the specific verb and resource: 'Poll a running audit by run_id'. It distinguishes this tool from get_report by explicitly routing completed audits to get_report with the same run_id, and it correctly references run_audit and list_audits as the source of run_id.

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?

The description gives explicit when-to-use guidance: keep polling every 15-30 seconds while status is pending/running, stop and call get_report when completed, and treat failed/cancelled as terminal states with structured reasons. It also names the provenance of the run_id, so an agent knows which sibling tools feed into this one.

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