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

Adds substantial context beyond the annotations: the write leaves results untouched and counts no check, a human reviews every report, and fixes only land in a later engine (implying no immediate effect). This complements readOnlyHint=false/destructiveHint=false with the actual side-effect scope and review latency.

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 the action and its arguments, followed by the behavioral payoff. No filler or repetition; every clause carries information.

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?

For a simple feedback-write tool with an output schema, full schema coverage and annotations that establish the write profile, the description supplies the missing pieces (no effect on results, human review, delayed fix). Nothing needed to invoke it correctly is absent.

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 100% and the schema already documents check_id, verdict, expected_action, note and text including retention/permission caveats. The description only restates the same fields ('the result's id, the verdict and ... the action it should have taken'), adding no syntax or edge-case detail beyond the schema.

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: report that a check got it wrong (or right), with the id, verdict and suggested action. It is clearly distinguished from the sibling check_* tools, which produce results, while this one reports feedback on 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 context for use: every report is read by a person and corrections ship in a later engine, and the verdict guidance covers the close-call 'correct' case. It never names an alternative tool or an explicit trigger such as 'call this after check_text returns a disputed result', so routing is inferred rather than stated.

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