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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description goes well beyond them: it names the consent/Do-Not-Call/quiet-hours/rate gates, notes a refusal identifies which gate fired, and warns never to claim delivery since the result only reports provider acceptance. That is unusually rich operational context for a mutation tool.

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 core action and channel choice, and each subsequent sentence carries distinct information (gates, per-channel requirements, email routing, delivery caveat). It is a dense single paragraph that runs long, but almost nothing is redundant.

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?

An output schema exists so return values need not be described, yet the description still clarifies that the result means provider acceptance rather than delivery. Combined with the gate and routing detail, an agent has everything needed to invoke this correctly.

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 already 88%, but the description adds real meaning beyond it: from_agent_id is sms-only and required, from is whatsapp-only and needed when multiple numbers exist, business_id is conditional on multi-business accounts, and lead_id ties to automation-pause state. Only the idempotency replay nuance is left to the schema text.

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 (send one message) and resource (a business's customer), and immediately enumerates the two supported channels (sms via an agent line, whatsapp via a connected number). It also names the excluded sibling (email_campaign) for email, so an agent can route correctly 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 per-channel preconditions: sms requires from_agent_id, whatsapp requires a connected number (pass from when there is more than one) and a customer who messaged in the last 24 hours. It also states the alternative for email and when business_id is required, leaving little to inference.

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