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

Annotations already declare idempotentHint=true, destructiveHint=false and readOnlyHint=false. The description adds real behavioral context beyond them: the operation does not dispatch anything ('Nothing is sent') and an empty body is a clearing/removal operation. It does not explain whether the write replaces or merges an existing draft.

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 short sentences, both front-loaded and load-bearing: the first states what it does and that nothing is sent, the second states the empty-body edge case. No filler.

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?

For a mutation tool with full schema coverage and a complete annotation set, this is nearly complete: it clarifies the no-send semantics and the clearing behavior. Minor gaps remain around overwrite/merge semantics and whether permissions or conversation state constrain the 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 coverage is 100%, so all three parameters, including the chat/note enum and the conversationId lookup hint, are already documented in the schema. The description's 'empty body clears the draft' merely restates the body property's own description, adding no new meaning.

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 (save) and resource (unsent reply/note in a conversation's composer), and the phrase 'Nothing is sent' immediately separates it from the send-oriented siblings like reply_to_conversation and accept_held_reply. An agent can identify the tool 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?

Gives clear context: use this to stage content 'so you can review and send it in the app', implying sending happens elsewhere, not through this tool. It stops short of naming the alternative send tool explicitly or stating when a draft should be discarded instead.

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