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

Annotations already declare destructiveHint=true and idempotentHint=true; the description adds real value by spelling out that the previous copy is replaced and is not restored by this tool, which makes the irreversibility concrete. It does not cover authorization needs or how the reviewId/id pair scopes the target.

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 tight sentences with no filler, and the destructive behavior is placed early. The leading 'APP:' token is minor noise but doesn't impede parsing.

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 and annotations cover the return shape and safety profile, but with zero required parameters and nine undocumented fields, the description leaves a meaningful ambiguity about whether id, reviewId, or both are needed to target a single item. That gap matters for correct invocation.

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 nine parameters, so the description must compensate, yet it only implies the meaning of id, subject, and body. reviewId, idempotencyKey, and the four external* correlation parameters are left completely unexplained anywhere.

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 and resource ('Overwrites subject and/or body on one per-contact email review item') with clear scope ('in the current review store'). The closing 'Does not send or launch' further separates it from send/launch-oriented siblings like launch_campaign and preview_message.

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 negative guidance ('does not send or launch') implies the tool is for editing draft copy before approval, but the description names no alternative and never says when to choose this over approve_review_item, reject_review_item, or list_review_items. Usage is inferable but not stated.

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