Create a Cardano tADA payment session for a pending guest order. Computes THB→tADA conversion, generates a payment session with 30-minute expiry, and returns payment details. Call this after placing a guest order to initiate payment. The payment is executed server-side using the GYOTAK A→B→A round-trip mechanism.
| Name | Required | Description | Default |
|---|---|---|---|
| order_id | Yes | Order ID (e.g. "BB-42") |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full responsibility for behavioral disclosure. It goes beyond 'create' by mentioning THB→tADA conversion, a 30-minute expiry, server-side execution via GYOTAK A→B→A, and that payment details are returned. This is solid coverage of key behavior, though it omits error cases and auth requirements.
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 three tight sentences with the main action front-loaded. Every sentence earns its place: the core function, the payment lifecycle details, and the usage trigger all contribute directly to correct tool invocation.
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 single-parameter tool, the description is largely complete: it states when to call it, what it computes, how it executes, and that payment details are returned. The absence of an output schema makes the return format underspecified, but the trigger and input requirements are fully clear for an agent to invoke it 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 100%, and the schema already provides an example for order_id. The description adds valuable context by specifying the order must be a 'pending guest order', which clarifies the expected state of the referenced order beyond the raw schema description.
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 clearly states the primary function: create a Cardano tADA payment session for a pending guest order, with additional specifics about conversion, expiry, and returned details. This differentiates it from siblings like check_payment_status and confirm_payment, which occupy later stages of the payment flow.
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 explicitly says to call this 'after placing a guest order to initiate payment', giving clear contextual sequencing relative to place_order. It does not explicitly name when-not-to-use or list alternative tools, but the placement in the workflow is unambiguous enough for correct selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clear role in the customer, ordering, payment, or verification flow. The only potential confusions (get_catalog vs search_fish, get_catch_reports vs verify_catch) are explicitly differentiated in their descriptions.
All tools follow a consistent verb_noun snake_case pattern using verbs like get, create, place, verify, check, and ask. Brand-specific tools like ask_gyotak and contact_gyotak still fit the same convention.
18 tools is slightly on the heavy side for a single server, but the scope spans sales, payments, customer management, and blockchain traceability, so most tools have distinct jobs. It is above the ideal range but not bloated.
The core commerce loop (register, order, pay, confirm) and traceability verification are covered well. Missing order cancellation, guest order status retrieval, or customer profile editing are minor gaps that agents can usually work around.