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

Annotations already declare readOnly=false, destructive=true, and idempotent=true. The description adds valuable behavioral context: the one-time confirmation code sent to the reviewer's email, the instruction to never fetch the code on the reviewer's behalf, and that the tool does NOT approve the draft. This goes beyond what annotations alone convey, though it stops short of explaining the destructive nature of the operation (irreversibility? email send?).

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?

Four terse, front-loaded sentences. The purpose is first, prerequisites next, then the critical email-code behavior and the non-approval caveat. No fluff, no repetition of schema fields. Every sentence carries information the agent cannot extract from annotations or schema.

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?

The description covers tool intent, prerequisites, email-code side effects, and a safety rule (don't fetch code), which is strong. But it omits what the agent should do with the result after a successful request (the tool likely returns a status or code), and it never explains the 'revision' structure beyond the schema. Given no output schema and a 50% parameter-coverage gap, the description is moderately complete but leaves the agent to infer how the exchanged idempotencyKey and revision object from the schema.

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 only 50% (only idempotencyKey is described), and the description does not explain the nested 'revision' object's fields (outputJobId, payloadHash). The description mentions review scope and reviewer role, but no mapping to the actual parameters, so an agent must rely on names alone. The idempotencyKey field already has a thorough schema description, so the text adds nothing new. This is a clear gap.

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 clearly states a specific verb ('Request'), a specific resource ('final review of this exact draft revision'), and includes an important distinction from approval ('This does NOT approve the draft'). However, it does not explicitly differentiate from the many sibling review-request tools (e.g., request_contribution_review, request_pack_review), leaving an agent to infer that 'final' is the unique qualifier.

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?

The description provides explicit prerequisites ('Requires a reviewer role and review scope, no unresolved blockers, and fresh source reads') and practical usage instructions (verify the draft, never retrieve the reviewer's code). It lacks an explicit when-not-to-use or alternative routing, but the context is clear enough for an agent to judge suitability.

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