send_channel_message

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

Annotations already declare openWorldHint=true and non-idempotent, so the risk profile is partly covered; the description still adds genuinely new context by stating no LLM is invoked, the text is transmitted verbatim, and provider-side constraints such as the Meta 24h window apply. It omits what happens on a rejected send (error vs silent drop) and whether provider limits are surfaced back to the caller.

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?

Three short sentences in descending priority: what it does, what it does not do internally, and which sibling not to use. No filler, no restatement of the title, and the most decision-relevant constraint (no LLM) 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?

Behavioral semantics for a non-idempotent, open-world delivery tool are well covered for such a short description, and no output schema exists to explain. However, with 6 parameters including an undefined nested options object and no guidance on message-vs-messages selection semantics or sourceLabel, an agent still cannot construct a non-trivial call from the description alone.

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 only 33% – agentId, convoId, options and sourceLabel carry no schema text at all, and options is a nested object with no defined shape. The description adds no parameter guidance beyond the implicit notion of a text body, so it fails to compensate for the coverage gap.

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?

Specific verb+resource ('Push an agent-initiated message onto the conversation channel') with the exact channel list enumerated, plus a clarifying negative ('Does NOT run the LLM — text is sent as-is') that pins down what kind of send this is. An agent can distinguish it from update_conversation_messages purely from the description.

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 exclusion with the sibling named ('Do NOT use update_conversation_messages for channel delivery (that only updates stored history)'), which is exactly the confusion this tool family invites. It stops short of routing the agent to the other delivery sibling send_sms or explaining when to use options/messages instead of plain text.

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