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

Beyond the annotations (readOnlyHint/openWorldHint/destructiveHint=false), it discloses that the payload is restricted to changed checks and that execution may be asynchronous with a 'running' status, which is the key behavioral trait an agent needs. It does not state whether the prior run is preserved or superseded, which matters for an operation that produces a new run.

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?

Three short sentences, front-loaded with purpose, then the paid-plan gate, then the async follow-up. No filler and every sentence carries information needed to invoke it correctly.

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 correctly explains the return value (only checks whose status changed, possibly a 'running' status). It is nearly complete for a one-parameter tool; the only gap is provenance of the input run_id.

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 0% for the single run_id parameter, so the description must compensate. It implicitly clarifies that run_id refers to the previous audit while the returned run_id is a new one, which is genuinely useful disambiguation, but it never says how to obtain a valid run_id or its format.

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 ('re-run a previous audit') plus the two defining constraints (same site and profiles, delta-only output). This clearly separates it from run_audit, which starts a fresh audit, and from get_findings, which fetches results.

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 a prerequisite ('Paid plans') and an explicit follow-up branch: if status is 'running', call get_findings with the new run_id. It does not explicitly say to use run_audit instead when no prior run exists, so the when-not case is only implied by 'previous audit'.

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