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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral value beyond that: the state machine (queued/running/completed/failed) and which fields appear in each state, plus the polling cadence. It does not say what happens to expired or unknown job_ids, which keeps it from 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?

Two short sentences, front-loaded with the verb and resource, then the state-to-field mapping and polling cadence. Nothing is redundant and every clause carries information the agent needs.

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 an output schema present, the description need not explain return values, yet it helpfully summarizes what each state returns. For a low-complexity single-parameter polling tool this is nearly complete; only edge cases like job expiry or invalid job_id are unaddressed.

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?

There is a single parameter at 100% schema description coverage, and the schema already documents job_id as coming from start_deep_audit. The description adds no additional parameter meaning, so the baseline of 3 applies.

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 ('Get a Deep Audit job's status') and enumerates the four lifecycle states with their payloads, so the agent knows exactly what it receives. It does not explicitly contrast itself with start_deep_audit, but the status-vs-start distinction is unambiguous from the wording.

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 concrete operational guidance — 'Poll every 5-10 seconds' — which is the key usage decision for a status tool. It stops short of naming alternatives (e.g., where to get the finished report via deep_audit) or stating when to stop polling, so it is clear context rather than full when/when-not guidance.

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