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

Annotations already declare destructive/non-idempotent/open-world, and the description adds substantial context beyond them: the ordered guardrail chain (blacklist, protected steps, blocking tags, channel pause, per-channel send caps), that a refusing guardrail is an immediate error with reason rather than a queued message, that success is only returned once the channel accepted and returned an identifier, that group messages are visible to all participants and flagged is_group=true, and that the action is irreversible.

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?

Long but dense, with purpose and targeting front-loaded before the guardrail and response semantics. Nearly every clause carries distinct information, though the guardrail/response block could be tightened slightly.

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?

No output schema exists, and the description compensates by describing the success response shape (returned only after channel acceptance with an identifier; is_group=true for groups) and the failure mode (explicit error, never a pending state). Nothing an agent needs to invoke and interpret this tool is missing.

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 the baseline is 3, but the description adds real semantics on top: the priority of conversation_id over lead_id+channel, and that recipient is verified server-side against the real contact (with 'sans nom' as the escape hatch) before anything sends, refusing with recipient_mismatch on disagreement. That is meaning beyond the raw field definitions.

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+resource+scope: sends a text message into an existing conversation, one-to-one or group, from the organization's account. This cleanly separates it from send_media (media) and schedule_message (deferred), which an agent can distinguish without opening any 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 targeting guidance: use conversation_id (recommended, and the only way for a group) or lead_id + channel, and always name the recipient in recipient. It stops short of naming sibling alternatives such as send_media or schedule_message, but the routing conditions it does give are concrete.

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