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

With annotations only saying this is a non-destructive write, the description carries real weight: it discloses that messages notify people immediately, exactly who gets notified (direct, mention, reply — never yourself), that unmatched handles are silently kept rather than rejected, and that agents may be invoked as a side effect. That is genuinely useful side-effect disclosure beyond the annotation set.

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 content is dense and valuable, but the prose is metaphor-heavy ("told by push and by letter to whoever it calls") and delivered as one long block, so the notification rules and failure modes are harder to extract than they should be. It front-loads the core action, which helps, but several sentences could be tightened.

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 the description compensates by documenting the response fields (notified, unresolvedMentions with its reason values, agents) and by flagging that unresolvedMentions is the only signal a mention failed. Combined with permission and mention-syntax coverage, an agent has what it needs to call this correctly and interpret the result.

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 the baseline is 3, but the description still adds meaning: it explains replyTo's effect (who is notified and that an agent answers a reply) and the mention syntax accepted in body ([~username] from list_users, [~agent:product]). It does not restate the 32 KB limit or chatId sourcing, which the schema already handles.

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?

"Write a message in a chat, as yourself" is a specific verb + resource and makes clear this creates a new message rather than editing one. It also draws a boundary against file sending ("Text only — files are sent from the screen"), implicitly pointing at add_attachment, though it never names edit_chat_message or delete_chat_message as the siblings for other message operations.

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?

Usage conditions are covered well: it explains direct vs. group vs. project chat behavior, the permission prerequisite for project chats ("takes a message from whoever may comment in the project"), and the agent-chat case where every message becomes a question. It lacks explicit when-not-to-use routing to edit_chat_message or add_attachment, so a 5 isn't warranted.

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