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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), and the description adds the non-obvious behavioral fact that this 'Never posts it: a person sends it from the app' — a publish-vs-save distinction the annotations do not convey. It stops short of covering idempotency (duplicate drafts on repeat calls) or auth requirements, so it is strong but not exhaustive.

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, front-loaded with what it does and the critical 'never posts' caveat before the alternative and example. Every sentence earns its place; the example is short and directly usable.

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 exists, so return values need no explanation, and the description covers the key behavioral concern (no publishing) plus routing to the alternative. It omits auth/permission expectations and what happens on repeated saves, which would complete the picture for a non-idempotent write.

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 both parameters are already documented, and the baseline is 3. The inline example illustrates the shape and how review_id pairs with text, but adds no constraint semantics (e.g. the 5970-char limit) beyond the schema.

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 gives a specific verb and resource ('Saves reply text ... as a draft on one review') and explicitly scopes it to drafts rather than published replies. It also names the distinction against siblings draft_reply (AI-written) and implicitly post_reply, so an agent can identify the tool without opening a 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?

It states when to use this tool ('reply text you wrote (or the user dictated)') and when not to, explicitly routing to draft_reply 'if you want Review Expert to write the reply.' The alternative is named with the condition that selects it, leaving nothing to inference.

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