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

Adds a great deal the annotations do not: irreversibility ('cannot be unsent'), audience scoping to people who wrote at least once, pacing of ~1 message per 30-45s per number, daily cap, working-hours respect, unsubscribe skipping, and the ban risk motivating variants. It does not say what the call returns or how to check progress afterward, and the 'cannot be unsent' framing sits slightly at odds with destructiveHint=false, though that is a nuance rather than a contradiction.

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?

Front-loaded with the irreversible-send warning in capitals, then prerequisites, then eligibility, then per-channel rules. Dense but every sentence carries operational weight; it is long only because the risk profile warrants it.

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 high-stakes, irreversible, non-idempotent send with 12 parameters and no output schema, the description covers the confirmation gate, audience eligibility, delivery pacing, and the anti-ban tactic. It omits what a successful call returns or how to monitor the broadcast after starting (the sibling list_broadcasts exists but is not referenced).

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 75%, and the description compensates for the highest-risk gap by explaining the body_variants/paraphrase strategy and why it matters (identical mass texts get numbers banned), plus the WhatsApp consent flag. It leaves tag, lead_status, and window_days entirely unexplained, so the undocumented quarter of the schema is still undocumentable from the description.

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?

Names a specific verb and resource ('Send one message to many clients of this project at once') and implicitly distinguishes it from the sibling preview_broadcast_audience, which it names as the required prerequisite. An agent can tell immediately this is the executing half of a preview-then-send pair.

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 an explicit gating procedure: run preview_broadcast_audience, show the owner the exact text and audience numbers, and start only after they say yes. It also names the channel-specific condition (consent_confirmed for WhatsApp), leaving no ambiguity about when this tool may be called.

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