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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutating nature is covered by structured data. The description contributes one real behavioral detail the annotations don't: 'none to clear it', i.e. the mark can be removed. It omits whether an existing mark is overwritten, whether the action is per-team scoped, and what confirmation is returned.

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, and the whole definition is two compact sentences. The enumerated mark list partially duplicates the schema's enum description, which is mild redundancy rather than bloat.

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 4-parameter mutation with no output schema, the description covers purpose and the meaning of each mark but says nothing about the optional team scoping (redirecting the action to another team) or the effect of overwriting an existing decision. Adequate to call the tool, but a destructive write deserves at least a note on irreversibility or prior-state handling.

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%, with the enum values and the run_id/finding formats fully documented in the schema itself. The description's 'name it by run_id and the finding's number' and its enum glosses largely restate that content rather than adding new meaning. Baseline 3 is appropriate when the schema does the explanatory work.

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 ('Record what the team decided about a finding') and enumerates the exact verdict vocabulary (known / watch / fixed / false_positive / none), which maps directly to the enum. It is clearly distinguishable from read-oriented siblings such as get_verdict or latest_results.

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?

The phrase 'as the verdict page's buttons do' anchors when this is appropriate, and the per-mark glosses ('not reported again', 'checked first next time') convey consequences of each choice. However, there is no explicit guidance on when to prefer this over adjacent tools like recheck, list_check_mistakes, or report_check_mistake, and no stated preconditions.

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