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

Annotations already declare this a safe, idempotent read, so the description only needs to add behavior beyond that. It does: it discloses the possible run states and the non-obvious conditional that the pass/fail verdict only materializes once the run is terminal. Polling semantics and whether findings are partial/paginated are left implicit.

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, front-loaded with what is returned and followed by the one conditional parameter behavior. No filler and nothing redundant with the annotations.

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 present, return-value detail is unnecessary, and the description covers states and the conditional verdict well. It omits how a run_id is obtained (list_runs) and whether findings arrive incrementally, which would help an agent polling this tool.

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%, so the description must carry parameter meaning, and it does for min_severity: it enumerates the allowed levels and explains the functional effect (adds a pass/fail verdict, only when terminal). run_id is left unstated, though its meaning is largely self-evident from context.

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 (fetch) and resource (status of one assessment run), then enumerates exactly what is returned: state values, findings so far, and phase progress. This cleanly separates it from siblings like list_runs (all runs) and cancel_run (mutation) without needing to name them.

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 clear operational context: fetch status for a single run, and supply min_severity only if a pass/fail verdict is wanted. It does not explicitly route the agent away from alternatives (e.g., list_runs to discover run_id, cancel_run to abort), so it stops short of full when/when-not guidance.

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