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

Annotations already declare readOnlyHint and idempotentHint, so safety is covered. The description adds genuinely non-obvious behavior: polling with wait:25 for client compatibility, that a timeout preserves the run and is resumable by ID, and that reading does not authorize a redesign. It doesn't cover the return shape, but annotations plus these constraints carry most of the burden.

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 payload, then the polling rule, then the completion handoff. Four sentences, each carrying a distinct rule. The final clause ('reading does not authorise a redesign') is terse but earns its place as a scope constraint.

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?

No output schema, yet the description names the returned contents enough for an agent to use the result. Covers polling, resumption, terminal-state distinction, and downstream routing. Missing only an explicit statement of what an incomplete run returns.

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%, so the description must compensate somewhat. It reinforces the wait:25 polling convention and the resume-by-ID semantics, which are the operative meanings of the wait param beyond the schema text. audit_id itself is undocumented in both places but is self-evident.

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 (read audit status) and enumerates the actual payload: progress, elapsed time, ranked findings with typed edits. This distinguishes it from siblings like get_audit_report (finished report) and ask_audit (interrogating evidence).

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 explicit when (use wait:25 while running), an explicit when-not ('a failed, cancelled or stalled run is not a finished report'), and routes to named alternatives (run_cro_skill, ask_audit) once complete. Nothing is left to inference.

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