send_whatsapp_message

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

With no annotations, the description thoroughly discloses the confirmation behavior: initial response with requires_confirmation=true, the need for user confirmation, the fact that success=false is normal, and the instruction not to retry. It also notes the mutation nature and the confirm parameter's role, providing full transparency for the agent.

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 description is relatively long but well-structured, starting with the main purpose, then phone format, then the crucial confirmation instructions. It uses emphasis effectively. While every sentence serves a purpose, it could be slightly more compact without losing essential information.

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?

The description covers the core sending function, phone format handling, and confirmation flow comprehensively. However, it omits details on post-confirmation behavior (e.g., success response), and lacks context for optional parameters and potential limitations like message length or rate limits, which would enhance completeness.

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?

The schema already describes all parameters (100% coverage), so baseline is 3. The description adds value by explaining how to handle phone numbers without prefix and emphasizes the confirm parameter's role, which is not fully captured in the schema. However, it does not add context for optional parameters like session_id, archive_after_send, or direction.

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?

The description clearly states that this tool sends a WhatsApp message to a phone number, specifying the action and resource. It distinguishes from sibling tools like create_whatsapp_template or update_whatsapp_profile by focusing on sending a one-off message, including the required phone format and confirmation process.

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?

The description provides explicit guidance on phone number format (E.164), instructs the agent to ask for country if no prefix is given, and details the confirmation flow (requires_confirmation=true, success=false, no retry). However, it does not mention when to use this tool over alternatives like scheduling or templating, missing explicit exclusions.

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