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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the description doesn't need to restate that. It adds valuable behavioral context: the 24-hour window, the public reply behavior on mention threads, and the 30-minute automation pause. It doesn't mention whether the message is irreversible or any rate limits, but the annotations cover the destructive nature. The description adds meaningful context beyond annotations.

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?

Four sentences, each carrying essential information: the core action, the critical time constraint, the mention-thread behavior, and the automation pause. No filler or repetition. The most important constraint (24-hour window) is front-loaded.

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 no output schema, the description covers the key behavioral constraints (24-hour window, public reply on threads, automation pause) and parameter nuances (draftId, workspaceId). It doesn't describe the success/failure response format, but the error case for window_closed is mentioned. Given the tool's complexity and the annotations covering safety, this is nearly complete.

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 80%, so the schema already documents most parameters. The description adds meaning for draftId ('AI draft that was waiting for approval') and workspaceId ('Only needed when the account has more than one — the error tells you the ids when it matters'). It doesn't add detail for text or mediaId, but the schema covers those adequately. The description compensates for the less obvious parameters.

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 states a specific verb and resource: 'Send a message in a conversation as the account.' It also distinguishes itself from siblings by clarifying that on a mention thread it posts a public reply, and by mentioning draftId for AI drafts. This clearly differentiates it from related tools like reply, approve_reply, and create_comment_to_dm.

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 description explicitly states the critical 24-hour window constraint and what happens outside it (refused with window_closed). It also gives guidance on when to use draftId and when to include workspaceId, including the instruction not to ask the person again. This is strong usage guidance.

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