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

With no annotations, the description carries the full behavioral burden and does so thoroughly: it only works for test customers, computes THB→tADA conversion, creates a preprod session with a 30-minute expiry, and creates nothing for unsupported order IDs. The side-effect boundary is clearly stated.

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 critical warning is front-loaded, and the two sentences pack in scope, exclusions, parameter constraints, behavior, and a time-bound expiry. 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?

The description is complete for selection and invocation, but with no output schema it only vaguely says 'returns the payment details' and does not specify the returned fields or how they connect to siblings such as check_payment_status. Minor gap in an otherwise strong definition.

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?

Although the schema already documents order_id and provides an example, the description adds crucial parameter-level meaning: the ID must belong to a GYOTAK test customer, and any other value causes a non-creating fallback. That materially changes how an agent should treat the parameter.

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 states an exact scope: a test/QA-only helper that creates a Cardano preprod payment session and returns payment details. It distinguishes itself from a production payment path by explicitly saying it is not for customer orders.

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?

It gives explicit when-to-use ('Test / QA only'), when-not-to-use ('do not use for customer orders', 'do not call it after placing a customer order'), and what happens with invalid input ('returns PromptPay guidance and creates nothing'). This leaves no ambiguity about whether the agent should select it for a real order.

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