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

Annotations declare destructiveHint=true and openWorldHint=true, but the description adds consequences an agent cannot infer: the message reaches a real person immediately, cannot be recalled or edited, and manual sending stands the agent down on that thread when `pauseBotOnManualMessage` is set. That side-effect disclosure is genuinely valuable beyond the structured hints. Minor caveat: the claim "there is no tool to delete a sent message" sits uneasily beside the sibling `message_delete`, which could mislead an agent about cleanup options, though that is a factual tension rather than an annotation contradiction.

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?

Front-loaded with the action and the irreversibility warning, and nearly every sentence carries an operational instruction. It runs slightly long, and the bot-pausing sentence plus the closing alternative list make it denser than strictly necessary, but no sentence is 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 non-idempotent, destructive send tool with no output schema, the description covers impact, irreversibility, consent protocol, channel variability, side effects, and the two safer alternatives. An agent has everything needed to decide whether to call it and how to prepare the user first.

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 `content`, `conversationId` and the nested attachment object are already documented, including examples. The description reinforces that `content` must be the exact delivered text and that the recipient must be named, but adds no syntax or format detail beyond the schema. Baseline 3 applies.

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 ("Send a message into a conversation") and immediately clarifies the delivery channel (LinkedIn or email depending on the thread). It also explicitly separates itself from `message_draft_ai_reply` and `conversation_update`, so an agent can route correctly without opening any 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 an explicit precondition (show the exact text and recipient, get an explicit yes before every call) plus two hard exclusions (never send copy the user has not read, never send to a thread they did not name). It names both alternatives and the condition that selects each: `message_draft_ai_reply` for a draft the user sends, `conversation_update` with `assistant: false` for a silent handoff.

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