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

Annotations only say non-read-only, non-destructive, closed-world. The description adds genuinely useful behavior beyond that: the text is forwarded verbatim to the CheckMyApp team, and a repeat report is deduplicated and returns 'joined: true' rather than creating a second entry. It stops short of covering error behavior (invalid scenario_id, mismatched run_id/journey/step combinations) or whether a submitted report can be retracted.

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?

Front-loaded with the action and the fix rationale, then targeting, then dedup behavior, in a logical order. It is one dense paragraph rather than segmented, and restating all four reason values ('not_checked', 'wrong', 'scenario_wrong', 'other') partially repeats the enum, which is the only real waste.

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 an 8-parameter mutation tool with no output schema, the description covers the targeting logic, the effect of submission, and the dedup outcome, which is most of what an agent needs. It omits the team parameter entirely (left to schema) and says nothing about what a successful non-duplicate submission returns, but nothing essential to calling it correctly is missing.

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%, so the baseline is 3; the description earns extra by explaining the alternative identification strategies as a coherent rule — 'run_id — optionally with a finding number, or a journey position and step position as get_review lists them — or by scenario_id' — which tells the agent these are mutually exclusive routes rather than independent fields. The enumeration of reason codes duplicates the enum and adds little.

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 concrete verb and object ('Report where CheckMyApp got a check wrong') plus the outcome of the action ('so the checker is fixed'), and enumerates the four mistake categories. Clearly distinct from sibling list_check_mistakes (which reads reports) and mark_finding (which annotates findings).

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 an explicit prerequisite workflow: 'list_check_mistakes shows what happened to each — look there first, so a mistake already reported is not reported again.' That is a real when-to-use rule with a named alternative. It does not state any case where this tool should not be used at all (e.g. reporting app-level failures vs. check mistakes), so it falls short of the full when/when-not bar.

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