submit_paymentquote_checkout で得た reservation_id と、エージェントが署名した x402 PaymentPayload（base64url）を渡して決済を確定する。サーバは facilitator 経由で on-chain settle し、確定した注文（order_number / tx_hash）を返す。署名は quote_checkout が返した payment_required の 内容に対する EIP-3009 TransferWithAuthorization であること。
| Name | Required | Description | Default |
|---|---|---|---|
| reservation_id | Yes | quote_checkout が返した reservation_id | |
| payment_signature | Yes | 署名済み x402 PaymentPayload（base64url JSON） |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description provides moderate transparency: it states the server settles on-chain via facilitator and returns order details. However, it does not mention potential failure modes, idempotency, or authentication requirements, which are important for a payment submission tool.
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 single, well-structured paragraph in Japanese that front-loads the key inputs and process. It is concise, with no redundant information, and every sentence contributes to the understanding of the tool's function.
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 inputs, server action, and outputs (order_number/tx_hash). It also highlights the signing requirement, which is critical. However, it could explicitly mention prerequisites (e.g., having called quote_checkout) and error conditions for a more complete context.
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?
Despite 100% schema coverage, the description adds significant semantic value by explaining that reservation_id comes from quote_checkout, that payment_signature is a base64url JSON of a signed x402 PaymentPayload, and crucially that the signature must follow EIP-3009 against the payment_required content. This goes well beyond the schema descriptions.
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 tool's purpose: it finalizes payment using a reservation_id from quote_checkout and a signed x402 PaymentPayload. It specifies the server action (on-chain settlement via facilitator) and the return values (order_number/tx_hash), distinguishing it from sibling tools like quote_checkout and get_order_status.
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 the tool should be used after quote_checkout and before checking order status, as it references obtaining the reservation_id from quote_checkout. It does not explicitly state when not to use it or list alternatives, but the workflow context is clear from the description.
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 clearly distinct purpose: order status, product details, shop details, listing products, listing shops, checkout quoting, searching, and payment submission. No overlap or ambiguity.
All tool names follow a consistent 'verb_noun' pattern in English, using lowercase with underscores (e.g., get_product, list_shops, submit_payment). The naming is predictable and uniform.
With 8 tools, the server is well-scoped for an e-commerce storefront. Each tool is necessary and focuses on core customer-facing operations (browse, search, checkout, payment, order status).
The tools cover the full customer journey: browsing shops and products, searching, initiating checkout with quote_checkout, submitting payment, and retrieving order status. No obvious gaps for the intended domain.