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

With no annotations, the description carries the full burden and does disclose one important trait: it does not send, so no external side effect occurs. It does not say whether the rewrite replaces the existing draft text in place or creates a new version, whether the original is recoverable, or whether approval is still required afterwards.

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?

The core sentence is tight and front-loaded, and the instruction example earns its place. The trailing '### Responses: **200**: Successful Response (Success Response) Content-Type: application/json' block is boilerplate that tells an agent nothing actionable and dilutes the definition.

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?

There is no output schema and no annotations, and one of the two required parameters is undefined, yet the description never says what comes back (rewritten text? a draft object? an ID) or what a handle is. For a two-required-parameter mutation tool with zero structured support, this leaves too much to guesswork.

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 0%, so the description must compensate. The instruction parameter is genuinely illuminated by the 'shorter' / 'propose Tuesday' examples, which show it is a free-text directive rather than a keyword. The 'handle' parameter gets no explanation at all, leaving it unclear whether it identifies a draft, a thread, or a person.

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: 'Rewrite a reply draft with an instruction', and gives concrete instruction examples ('shorter', 'propose Tuesday'). The resource name itself ('reply draft') separates it from rewrite_draft, rewrite_comment_draft and rewrite_content_draft in the sibling list, though the description never makes that distinction explicit.

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?

'Does not send' implies this is a safe pre-send editing step, which hints at where it sits relative to draft_reply and approve_reply_draft. However, it never states when to rewrite versus re-draft or edit, nor any precondition such as the draft needing to exist in a particular state.

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