submit_mapping_review

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

Annotations cover the safety profile (non-read-only, non-idempotent, non-destructive), and the description adds genuinely new context: reviewer-principal authorization and the fact that approval is bound to the content hash of items under review (implying stale approvals are rejected). It stops short of describing retry/idempotency behavior or what happens to prior decisions.

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?

Short and front-loaded: purpose sentence first, then eligibility and decision vocabulary. The embedded line breaks and indentation are slightly noisy but no sentence is wasted.

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?

Output schema exists, so return values need no explanation, and annotations carry the mutation safety profile. For a 3-param mutation tool the description covers the essential decision vocabulary and the content-hash binding, leaving only minor gaps around run state prerequisites and array completeness.

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%, so the description must compensate. It does document the decision values (approve | reject | approve_with_override) and the override keys, which mirrors the sparse schema description. But run_id and comment semantics, and whether the decisions array must cover every pending item, remain undocumented.

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+resource: 'Record a human reviewer's decisions for the run's current gate', with a clear scope (current gate of a run). It is distinguishable from list_pending_reviews and certify_run by its reviewer-decision focus, though it does not name a sibling explicitly.

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?

'Reviewer principals only' gives an eligibility constraint, and the enumerated decisions imply what the call is for. However, there is no explicit when-to-use guidance versus adjacent tools such as certify_run or resume_run, nor an indication of what state the run must be in before submission.

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