record_review

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

Annotations only declare the mutation/interactivity profile (readOnly=false, idempotent=false, closed world). The description adds genuinely non-derivable behavior: a human is prompted for name and rationale, the agent cannot supply them, and a non-answer records nothing. That human-in-the-loop and failure-mode detail is exactly the context annotations can't carry.

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 core action, with the human-prompt constraint and the failure mode each getting one clause. Nothing redundant; every sentence carries distinct information.

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?

An output schema exists, so return values need no explanation, and the annotations cover the safety profile; the description covers the crucial human-in-the-loop semantics and the no-op case. The only real gap is the undocumented parameters, which is a schema-side deficiency more than a description one.

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% and there are 2 required parameters, so the description must compensate — yet neither req_ids nor decision is mentioned, and the approve/reject boundary of decision is left to the schema. 'Requirements' and 'sign off' only loosely gesture at the parameters.

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?

The description states a specific action (record a human sign-off on requirements) with the key distinguishing trait that a HUMAN, not the agent, makes the call. That differentiates it from automated siblings like run_verification or flag_requirement_issue, though it never names 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?

Usage is implied by the sign-off semantics ('ask a human to sign off requirements'), and it notes the no-response outcome, but it never states when to prefer this over flag_requirement_issue or how it relates to run_verification/evidence_report. No explicit when-not or alternative routing.

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