record_review

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

Annotations already declare readOnly=false, idempotent=false, destructive=false. The description adds valuable context beyond that: it discloses the resulting state transition ('Moves the proposal to pending_approval') and an authorization constraint on the reviewer's model family. It does not warn that non-idempotency means repeated calls may create duplicate reviews, which is a minor gap.

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?

Three short sentences, front-loaded with the action and verdict values, then the constraint, then the effect. Every sentence carries information; 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?

Captures purpose, a prerequisite, and the downstream state change, which is solid for a mutation tool with no output schema. But with 5 parameters at 0% coverage, the definition is incomplete on inputs (ref semantics, what notes should contain, confidence's role) that an agent needs to call it correctly.

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 5 parameters, so the description carries the full burden. It clarifies two of them—verdict (enum values) and reviewer_model (must be a different model family)—but leaves ref, notes, and confidence completely unexplained, so half the surface remains opaque.

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 (Record) and resource (the independent reviewer's verdict), and enumerates the allowed values AGREE|DISAGREE|SPLIT. This distinguishes it from sibling mutation tools like record_owner_decision and confirm_done, though it never names the alternative it differs from.

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 one concrete precondition—the reviewer must be a different model family from the GM—which is genuinely useful usage context. However, it offers no explicit when-to-use framing versus siblings like record_owner_decision, and no guidance on whether this is the sole path to pending_approval.

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