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

Annotations already declare destructive=true, openWorld=true, idempotent=false; the description adds genuinely new behavioral facts — that no LLM generation occurs, text is transmitted verbatim, and provider-side delivery windows can block the send. It does not discuss retry/failure semantics or whether the sent message is persisted to history, which would matter given non-idempotency.

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, each doing distinct work: what it does, what it does not do (no LLM), and what to avoid. Front-loaded with the action and zero 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 destructive, open-world send tool with no output schema, the description covers the highest-risk facts (verbatim delivery, no generation, provider restrictions) and the sibling trap. The remaining gap is failure/response behavior and history-persistence, which an agent would likely want before retrying a non-idempotent send.

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 only 33% across six parameters, and the description adds no parameter-level meaning at all — nothing about agentId/convoId semantics, what 'options' contains, or what sourceLabel does. The message/messages mutual exclusivity is only implied by the schema's own field descriptions, so the description 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?

States a specific verb+resource ('Push an agent-initiated message onto the conversation channel') and enumerates the concrete channels (WhatsApp, Messenger, Instagram, Telegram, SMS, Discord). It also pre-empts confusion with a sibling by naming update_conversation_messages and clarifying that this tool performs actual delivery.

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 negative routing rule ('Do NOT use update_conversation_messages for channel delivery') plus the condition for provider constraints (Meta 24h window). It stops short of covering the overlapping send_sms sibling or when to prefer the structured 'messages' form over plain 'message', so it is clear but not exhaustive.

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