send_message

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

Without annotations, the description carries full behavior disclosure burden. It mentions a default (use_profile_webhooks defaults to True) and a behavior (auto_detect for long SMS), but doesn't cover side effects, costs, delivery guarantees, or that sending may be asynchronous. The Returns field is vague ('Dict[str, Any]').

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 uses a clean Args/Returns structure with each field on a single line. It is somewhat long due to the number of parameters, but every line provides useful information. No fluff or repetition.

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 tool is complex (many parameters, no annotations, no output schema, nested schema object), but the description is only a parameter list. It fails to explain how arguments relate to the 'request' object, what kind of response to expect, or any operational context (e.g., network needs, message delivery). This is insufficient for safe invocation.

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 0%, so the description must compensate with parameter meaning. It lists 11 fields with types and defaults, but critically fails to map them to the actual schema, which expects a single 'request' object. The description does not state that these arguments belong inside 'request', leaving invocation ambiguous and prone to error.

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 opens with 'Send a message', a clear verb+resource statement. It is distinct from sibling tools like make_call, get_message, or send_dtmf. However, it doesn't explicitly highlight SMS/MMS support or exclusions, though the 'type' parameter hints at it.

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?

No guidance is provided on when to use this tool versus alternatives like start_assistant_call or send_dtmf. There are no prerequisites, exclusions, or references to related tools. The description only explains parameters.

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