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

Annotations already declare readOnlyHint=true, so safety is covered. The description does add genuinely useful semantics beyond that: the state enumeration, and the notable caveat that 'unknown' means the count could not be made and is never reported as zero, which prevents a serious misreading of the result.

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?

One compact sentence that front-loads the state list and parenthesizes the important 'unknown' caveat. The trailing capability tag is noise for an agent, and the sentence is a noun fragment rather than a statement of what the call does.

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 one required parameter, no output schema, and readOnly annotations, the definition covers the state vocabulary but not the shape of the 'result' payload the tool name promises. An agent knows what states to expect but not what a completed audit 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 description coverage is 0% for the single audit_id parameter, so the schema itself adds nothing. The description partially compensates by tying the id to 'an audit started with run_audit', implying provenance, but it never states format, length limits, or what happens with an unknown or expired id.

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 names the resource (an audit started with run_audit) and what it yields (state and result), and enumerates the possible states. It distinguishes itself from the sibling run_audit by being the read-back side, though the verb is only implied by the fragment 'The state and result of...' rather than stated as 'retrieve'.

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?

Usage is implied rather than stated: the phrase 'started with run_audit' tells an agent this is the follow-up call to a run_audit invocation. There is no explicit guidance on polling cadence, whether to call repeatedly until 'complete', or what to do on 'failed' or 'unknown'.

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