draft_review_reply

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

Annotations only say readOnlyHint=false and non-idempotent; the description adds non-obvious behavior — that it consumes exactly one Review AI credit and that it only returns a draft rather than persisting anything. That cost and side-effect disclosure goes beyond the structured fields.

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 sentences, purpose front-loaded, then parameter semantics, then the routing/credit note. Efficient, though slightly dense with parentheticals.

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?

With no output schema, the description correctly tells the agent what comes back ('the draft is returned only') and notes the credit cost. Adequate for a generation tool; it stops short of describing the returned text's language/format details beyond 'in the storefront's language.'

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 coverage is already 100%, so baseline is 3, but the description adds real meaning by explaining the division of labor: the review's rating/text are pulled automatically while `note` carries the developer's intended message (a fix shipped, a setting to try). That clarifies the semantic role of `note` beyond its schema text.

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 ('A developer reply draft for one review') and immediately distinguishes itself from the sibling reply_review by noting the draft is returned only. An agent can tell what this produces without opening the schema.

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?

Explicitly routes the agent: 'The draft is returned only — reply_review posts a reply after your confirmation,' which names the alternative and the post-draft step. It lacks explicit when-not conditions, but the draft-vs-post distinction is clearly drawn.

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