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

Annotations already declare readOnly, idempotent, and non-destructive, so the safety profile is covered. The description adds genuinely useful non-annotation behavior: the expected poll cadence, the 3-minute bound, and that structured completion carries compact reportSummary evidence once the stored report is ready.

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 tight sentences, zero filler, with the trigger condition front-loaded before the polling mechanics. Every clause earns its place.

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?

An output schema exists, so return values need not be enumerated, yet the description still flags the notable reportSummary field. For a one-parameter polling tool with full annotation coverage, nothing needed to call it correctly is missing.

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% and there is a single auditId parameter, so the schema already carries the semantics. The description only implies that the ID comes from run_audit's response and adds no format or sourcing detail beyond that, which is the baseline case when the schema does the heavy lifting.

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 positions this as the poller for an audit kicked off by run_audit and indicates it surfaces completion plus a reportSummary, which lets an agent distinguish it from run_audit, get_audit_report, and get_audit_history. It never states outright 'returns the current status of an audit', so the core verb+resource is inferred from the name and the trigger sentence rather than declared.

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?

Explicit trigger ('Call after run_audit returns queued or running') plus concrete polling policy (every 20 seconds, up to 3 minutes) is unusually actionable guidance. It stops short of naming the follow-up alternative (e.g. get_audit_report once the report is ready), so the routing after completion is left implicit.

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