Server defines 6 tools with complete input schemas and descriptions in Chinese. Naming follows verb_noun pattern (create_order, get_order, list_orders, set_address). However, descriptions lack English translations and are terse (avg ~80 chars). Parameter descriptions are minimal, most lack format/range guidance. No output schemas documented. Error handling returns raw API errors without recovery guidance. No tool annotations (readOnlyHint/destructiveHint). Missing idempotency guidance for write operations. Schemas are present but sparse on constraints (e.g., amount_usdt range stated in description but not as JSON Schema min/max).
公开查询一笔订单的支付状态(无需鉴权,适合轮询)
创建一笔 USDT(BSC) 收款订单。商户须为 active 且已绑定收款地址(set_address)。返回订单号、精确转账金额、收款地址与收银台链接
查询自己名下一笔订单的详情(需 API key)
列出最近 50 笔自己的订单
查看当前商户资料(状态、绑定地址、回调、余额等)
绑定/更新商户的 BSC 收款地址与回调地址
No output schemas documented. LLMs cannot predict response structure or plan downstream tool calls. create_order, get_order, list_orders, merchant_me lack documented return types.
Descriptions are in Chinese only and lack English translations. Non-Chinese-speaking agents and developers cannot understand tool purpose or when to invoke them.
Parameter descriptions lack format/range constraints. E.g., 'amount_usdt' states range in description text but not as JSON Schema minExclusive/maxInclusive. 'address' requires BSC format (0x + 40 hex) but no regex pattern or validation hint.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 61 | 2026-07-28+ | v2 |
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). Agents cannot distinguish safe reads (get_order, list_orders) from writes (create_order, set_address) without parsing descriptions.
Error handling returns raw API error messages without recovery guidance. E.g., 'clawpay.click POST /api/orders failed: ...' gives no actionable next step. Should suggest 'Ensure merchant is active and address is bound via set_address().'