send_message

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

With no annotations, the description carries the full burden and does supply real behavioral context: which permission each mode requires and that contact-sender messages need an extra scope. It does not disclose side effects (whether an email is actually delivered, notification behavior), rate limits, or error modes, so it is helpful but incomplete for a write operation.

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 permission constraints are front-loaded after a one-line title, and the endpoint line adds orienting detail. The repeated 'Send Message' header and the low-value 'Tags: Conversations' line are minor waste but nothing obscures the actionable content.

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 annotations and no output schema, the description covers auth requirements but not what is returned, whether the send is idempotent via echo_id, or how threading via source_id behaves at the tool level. Adequate but leaves meaningful gaps an agent would want filled.

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%, so a 3 is the baseline, but the description goes further by tying `private: true` and `sender_type: contact` to distinct permission requirements — meaning the agent could not infer from the schema alone. It supplies no extra clarification for `mentions`, `echo_id`, or `source_id`, which keeps it from a 5.

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 states a clear verb+resource ('Send Message') and pins it down with the concrete endpoint POST /api/v1/conversations/{cuuid}/messages, so an agent knows a message is created inside a specific conversation. It is distinguishable from siblings like get_message or delete_message by the POST/create framing, though it never explicitly contrasts with them.

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?

There is no explicit when-to-use vs when-not-to-use guidance and no naming of alternatives. The permission block (messages:write, messages:write_private, messages:write_as_contact) tells the agent about preconditions for variants, but that is prerequisite info rather than routing guidance between tools such as retry_message or apply_macro.

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