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

Annotations cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds real behavioural context beyond them: conditional output depending on signed-report state, an empty list when all cells pass, and the explicit limitation that no fix suggestions are included because the engine records only observations.

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?

Purpose is front-loaded in the first clause, but the text is a dense run-on that enumerates the same field lists twice across the two branches and is heavier than the decision it supports.

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 carries the full burden of explaining returns and does so thoroughly for both branches, including the all-passed empty case. The remaining gap is parameter meaning, not return behaviour.

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% and the single required parameter is never mentioned in the description — no format, no source, no constraints. Even though 'run_id' is self-explanatory by name, the description does nothing to compensate for the coverage gap.

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 ('Returns the cells that did not pass') plus the scope condition (a complete run). An agent can tell this is a failure-detail listing rather than a status or report tool, though it never names the siblings it is distinct from.

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 does describe the branch condition that changes behaviour — signed report present vs. not — which implies when you get which payload. But there is no explicit guidance on when to call this over get_report or get_run_status, and no stated prerequisites for obtaining run_id.

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