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

The description headlines 'Idempotent transactional messages', but the annotations declare idempotentHint: false, a direct contradiction of the tool's stated core behavioral trait. Although the description otherwise adds genuinely useful behavior (per-call cost, async→get_outcome handoff, honest failure on unconfigured channels), the explicit conflict with the annotations is disqualifying.

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-loads the message classes first, then appends cost, async and availability flags in dense bracketed notation. Every clause carries information, though the tag-style brackets ('[async→get_outcome]') are slightly cryptic and require schema knowledge to parse fully.

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 5-param, nested-object, no-output-schema mutation, the description covers cost, failure semantics, async result retrieval and a deployment-level channel restriction. What is missing is any statement of return shape or delivery-receipt format, and the idempotency claim is inconsistent with the annotations.

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% across 5 params, and the description compensates meaningfully: it clarifies idempotency_key replay semantics, the async result path (get_outcome), and most importantly that SMS is unavailable on this deployment, which overrides preferred_channel's 'sms' default. It does not explain the recipient/name/data payload shape, which the schema covers only partially.

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+resource (send transactional confirmations) and enumerates the concrete message classes it covers (OTP, booking confirmation, payment receipt, cancellation notice), which clearly differentiates it from the generic sibling send_message. An agent reading only this line knows exactly what business event this tool serves.

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 clear usage context: transactional (not conversational) messages, cross-channel fallback, and an explicit deployment limitation ('Not available on this deployment: SMS') that constrains channel choice. It does not, however, explicitly state when to prefer this over send_message or get_conversation, so a routing decision against siblings is only implied.

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