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

Annotations already indicate destructive, idempotent, non-read-only behavior. The description adds extra behavioral detail: it revalidates source evidence, prohibits retrieving the reviewer's code, and rules out production agreement approval. These go beyond the annotations without contradicting any of them.

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 short sentences each earn their place: purpose, validation behavior, production-agreement exception, and a security rule. The core purpose is front-loaded, and no filler or redundant wording is present.

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?

Given 3 parameters, a nested revision object, and no output schema, the description covers high-level intent but misses parameter semantics for itemId and revision. The source perspective is clear, but a precise caller would need to look elsewhere for field meanings and expectations; this is a moderate gap.

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?

The schema description covers only the idempotencyKey (33% coverage), and the tool description does not clarify itemId or the revision object. 'One exact file revision' hints at revision but leaves outputJobId and payloadHash unexplained, so the agent cannot fully infer what values to supply.

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 names a specific verb ('Request'), a concrete object ('reviewer email confirmation'), and a narrow scope ('one exact file revision after reading the actual file'). It also adds distinguishing constraints ('Production agreement does not approve this file', 'Never retrieve the reviewer's code'), clearly separating it from siblings like confirm_document_review or request_review.

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?

It gives an explicit prerequisite ('after reading the actual file') and a meaningful context signal ('Revalidates source evidence and current versions'). It does not explicitly name alternative tools or when not to use them, but the stated scope and constraints provide firm, clear usage context.

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