ghl_conversation_send_message

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

Annotations indicate readOnlyHint=false and destructiveHint=false, and the description adds context about PHI-adjacent data and required fields. However, it does not disclose side effects like triggering notifications or updating conversation state. No contradiction with annotations.

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 front-loaded with critical warnings (PHI-adjacent, required fields) and is mostly concise. A few extra details could be trimmed, but overall well-structured.

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?

Given the complexity (nested object, many optional fields) and no output schema, the description covers usage well but omits return value details. It could be more complete about what the response looks like.

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%, but the description adds value by noting that 'status' is unusual for outbound sends yet required, and instructs to populate type-appropriate fields (message/html/subject for Email, fromNumber/toNumber for SMS, attachments as URLs). This goes beyond what the schema defines.

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 'sends a message on a real conversation thread' and 'Send a new message', specifying the verb (send) and resource (message). It distinguishes from sibling tools like ghl_conversation_add_inbound_message by emphasizing the real conversation thread context.

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 that all four required fields must be supplied or the API returns 400, and advises to populate type-appropriate fields. However, it does not explicitly state when to avoid this tool versus alternatives like ghl_conversation_add_inbound_message.

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