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

Adds substantial behavior beyond the annotations: channel fallback semantics, an explicit honest-failure guarantee ('fails honestly rather than reporting a delivery that did not happen'), per-call cost and the condition under which it is not charged, and async retrievability. Minor tension: the description calls the messages 'Idempotent' while idempotentHint=false, though the schema's idempotency_key (24h replay) reconciles this as key-scoped idempotency rather than default behavior.

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?

Information-dense and front-loaded: the artifact types come first, then fallback semantics, then cost/async/deployment brackets. The bracketed shorthand is efficient but slightly telegraphic; every element still earns its place.

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?

With no output schema, the description usefully supplies the async retrieval path (get_outcome), the cost model, honest-failure semantics, and the SMS unavailability — enough for correct invocation. Residual gaps are the recipient/data payload expectations left to a schema that is only 40% documented.

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 description coverage is only 40% across 5 params with a nested recipient/data object, so the description must carry more weight than it does. It does add meaning for channel behavior ('falls back across configured channels') and idempotency, and its type list overlaps the confirmation_type enum, but it never explains the data payload shape or recipient fields.

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 ('transactional messages') and enumerates the concrete artifact types (OTPs, booking confirmations, payment receipts, cancellation notices), which maps directly onto the confirmation_type enum and separates it from the generic send_message sibling. An agent can identify the tool's domain without opening the 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?

Provides clear operating context: it routes the agent to get_outcome for async results ('async→get_outcome') and states an exclusion ('Not available on this deployment: SMS'). It does not, however, explicitly contrast this with the sibling send_message, so the when-to-use boundary between transactional and general messaging is left to inference.

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