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

Annotations already indicate destructiveHint=true and readOnlyHint=false, so mutation is known. The description adds value by explaining idempotency (replay returns original receipt, no re-charge) and honest failure on unconfigured channels, which are important behavioral traits beyond the annotations. However, it does not mention cost implications beyond the $0.02/per_call tag, which is minimal. No contradiction with annotations.

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 description is a compact three-sentence block that front-loads the core purpose and then adds crucial behavioral details. Every sentence carries weight: purpose, fallback/honest failure, idempotency and pricing/asynchronous pattern. No fluff or redundancy.

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?

Given the tool's moderate complexity (5 params, nested objects, enums) and lack of output schema, the description is nearly complete. It explains idempotency, cost, async pattern, and type-specific data. Minor gaps: exact response format is not specified (no output schema), and the 'reminder' type is not described, but the description covers enough for a competent agent to invoke 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 only 40%, so the description must compensate. It directly explains 'data' is type-specific (e.g., otp_code, appointment_time) and clarifies 'idempotency_key' semantics (24h replay returns original receipt). This adds meaning beyond the schema. However, it doesn't detail 'recipient' or 'preferred_channel' beyond the schema, but those are self-evident. Overall, it compensates well for the gap.

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 explicitly names the tool as 'Idempotent transactional messages' and enumerates concrete use cases (OTPs, booking confirmations, payment receipts, cancellation notices), clearly distinguishing it from the sibling 'send_message' which likely handles general messaging. The specific verb 'send' and clear resource scope make the purpose unmistakable.

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?

The description implies usage for transactional messages and briefly mentions channel fallback behavior, but it does not explicitly state when NOT to use this tool or name alternatives like 'send_message' for non-transactional messages. The context is clear from the examples, but lacks explicit exclusions.

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