Get results of an earlier audit run

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is settled. The description adds context beyond them: no new scan is started and there is no additional cost. Return shape is covered by the output schema, so nothing further is owed there.

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 sentences, no filler. The core action and the runId key lead, with the 'does not start a new scan' caveat placed where it prevents misuse.

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 and rich annotations, the description need only cover scope and cost, which it does. The one hole is the near-duplicate sibling get_run_results, which an agent could easily pick instead.

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 100% and the schema already explains that runId comes from an earlier result and that check selects the result parser. The description adds essentially no parameter detail beyond that, so the baseline 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?

The description uses a specific verb and resource ('Fetches the status and results of an audit run') and pins the lookup key to runId. It also rules out starting a new scan, which separates it from the audit_* / scan_* siblings. It does not distinguish itself from get_run_results, the closest sibling.

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?

It gives a concrete trigger: use when a run was still 'running' when its launching tool returned, or for any earlier run. The negative case ('Does not start a new scan') is stated outright. It omits any routing guidance versus get_run_results.

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