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

Annotations only say readOnlyHint=false and destructiveHint=false; the description goes further by disclosing the 403 self-report restriction and the overwrite semantics ('The latest result per gate kind counts'). It also sketches the expected evidence payload and the extra items array required for ACCEPTANCE, which is real behavioral context beyond the annotations. It doesn't describe permissions or what happens if neither target is supplied.

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 purpose and target selection, but the inline pseudo-JSON for evidence and items is terse and slightly cryptic, forcing the agent to parse a half-schema sentence. It is compact with little filler, though readability suffers.

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 mutation tool with an output schema and non-trivial nesting semantics, the description covers the essential mechanics: target selection, evidence shape, ACCEPTANCE item coverage, the self-report prohibition, and latest-wins behavior. The main remaining gap is the undocumented source parameter and the absence of a rule for what happens when both task_key and claim_id are omitted.

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% across six parameters, so the description must carry the load and only partly does: it explains task_key vs claim_id and spells out evidence and ACCEPTANCE items. The source enum (RUNNER vs AGENT_CLAIM), the meaning of PASS/FAIL/ERROR/SKIPPED, and the gate_kind values remain unexplained beyond their enum names.

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 a machine gate result') and names the two target types, task_key or claim_id, so an agent can tell it records gate outcomes rather than verifying or reviewing them. It doesn't explicitly contrast against siblings like verify_change_claim or review_task, which keeps it at 4.

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 use context: report a result for either a task or a change claim, with the ACCEPTANCE form requiring per-item coverage. It also states a hard exclusion — an executor may not report its own ACCEPTANCE (403 acceptance_self_report) — and notes that only the latest result per gate kind counts, but it never names an alternative tool for cases where this one doesn't apply.

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