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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description adds genuinely non-obvious context: the same tuned generator the app uses, the business's saved voice and sign-off, and that the draft is persisted into the app editor. It does not clarify whether an existing draft is overwritten (which is what the destructive hint likely refers to) or whether repeated calls regenerate variants.

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?

Two sentences, both load-bearing, with the primary action and its persistence effect front-loaded and the safety guarantee last. No filler or restatement of the tool name.

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?

Covers action, persistence destination, and the no-publish guarantee for a two-parameter mutation tool with no output schema. The remaining gap is what the caller receives back and whether an existing draft is replaced, which matters given destructiveHint=true.

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 100%, so review_id's provenance ('UUID from list_reviews') and instructions' format and 300-char cap are already documented in the schema. The description adds only that drafting is scoped to 'one review', which is a baseline contribution when the schema does the heavy lifting.

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 (generate), resource (reply drafts), and scope (one review), plus where the result goes ('appears in the app's editor'). It is immediately distinguishable from publish_reply by the explicit 'drafts only' clause.

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 'NEVER publishes anything - drafts only' line clearly establishes this as the pre-publish step, which routes the agent away from publish_reply. It stops short of naming publish_reply as the follow-up tool, so the when-to-use guidance is clear but not fully explicit about the alternative.

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