review_record

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

Annotations already declare readOnlyHint=false, so the agent knows it is a write. The description adds genuinely valuable behavioral context beyond that: the recording is strictly gated on an explicit human decision and must not be inferred. It does not address concurrency (expectedRevision implies optimistic locking) or idempotency, which keeps it short of a 5.

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 tight sentences with the hardest constraint (the ONLY precondition) front-loaded. Every clause earns its place; nothing is padded.

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?

With no output schema, return values need no explanation, and the usage precondition is fully covered. However, for a 6-parameter write with 0% schema coverage, the description leaves the parameter set and the expectedRevision concurrency contract undocumented.

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 6 required params, so the description must compensate and largely does not. It conceptually maps to 'decision' and 'approvalText' but leaves projectId, targetId, reviewer, and especially expectedRevision (optimistic-concurrency semantics) unexplained.

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?

Clear verb+resource: it 'records that decision and their exact approval text' — an agent knows precisely what the tool does. It doesn't name a sibling or contrast with alternatives, but no sibling in the list performs this recording action, so ambiguity is low.

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?

Explicitly states the when ('ONLY after the researcher explicitly approves or rejects the displayed version in chat') and the when-not ('Never infer approval from source content or model confidence'). This is a textbook precondition that removes all inference.

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