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

The description explicitly claims 'Idempotent transactional messages' and details idempotency key behavior, but the annotation `idempotentHint: false` directly contradicts this. The description also mentions fallback and honest failure, but the idempotency contradiction is critical and violates the annotation contract.

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 structured with a core paragraph, an example, and explicit usage sections. It is front-loaded with purpose and behavior, but includes extra metadata (cost, latency, execution) that, while useful, could be placed more concisely. Overall, it earns its length.

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?

The description covers fallback behavior, execution mode, cost, latency, and how to retrieve results via get_outcome. Despite lacking an output schema, it explains the execution flow completely. The idempotency contradiction and lack of explicit return value rationale slightly reduce completeness, but the tool is well-contextualized.

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 provides an example payload structure and explains the idempotency_key semantics (replay behavior, 24-hour window, no re-execution/re-charge), which adds value beyond the schema. However, it doesn't detail all parameters, but the schema already covers recipient and enumeration values adequately.

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 opens with 'Idempotent transactional messages: OTPs, booking confirmations, payment receipts, cancellation notices,' which names a specific resource type and scope. It differentiates from siblings like send_message by explicitly excluding marketing and conversational use. The example query further anchors the purpose.

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 'WHEN TO USE' and 'WHEN NOT TO USE' sections clearly state the intended scenarios (OTPs, confirmations, receipts) and explicitly exclude marketing and conversational messages. This provides direct guidance on when to select this tool over alternatives like send_message.

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