send_message

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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false; the description adds context those annotations cannot carry — that delivery reaches a real person's phone, that a confirmation step is expected, that idempotency_key is mandatory (body or header) with duplicate-replay returning the original result, and that channel-specific cold-start constraints apply. It stops short of covering failure modes, per-channel rate limits, or what a partial failure returns.

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 verb and payload types, then routing, then channel constraints, then the safety warning — a logical progression with almost no filler. The opening 'Send a message.' is slightly redundant with the title and the annotations-supplied title text, but the rest of the prose is dense and purposeful.

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 12-parameter mutation tool with no output schema, the description covers routing, channel eligibility, idempotency, and human-confirmation requirements. The remaining gap is mapping the action enum values (react/unreact/typing_on) to their parameter sets explicitly, though the schema's field descriptions largely bridge that.

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?

With 12 parameters at 67% schema coverage and zero required fields, the description supplies the missing decision logic: which parameter combinations are valid routing keys and which two channels accept to_phone. It also ties payload type to parameter intent (template vs reaction vs typing indicator), adding meaning beyond the terse per-field schema text.

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') and immediately enumerates the payload types it covers (text, WhatsApp template, reaction, typing indicator). It is clearly distinguishable from read-side siblings like list_messages or get_conversation, so an agent can pick it without opening the 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 explicit routing selectors (conversation_id, platform plus platform_user_id, to_phone) and hard eligibility rules: SMS/WhatsApp/Telegram may start cold, Facebook and Instagram require a prior inbound message. It also states the pre-call obligation to confirm recipient and text with the user, which functions as an effective when-to-use gate.

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