refund_payment_order

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

Without annotations, the description discloses key behaviors: the asynchronous nature (accepted/processing vs final success) and uniqueness constraint. It does not detail permissions or side effects, but covers the most critical traits.

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?

Three concise sentences front-load the action, include critical constraints, and direct to next steps. No wasted words.

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?

Given no output schema and no annotations, the description adequately covers the async refund submission process and directs to a sibling tool for confirmation. Some parameter details are missing, but overall context is sufficient.

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?

The description adds meaning to two of four parameters: order_no (platform identifier) and mch_refund_no (must be unique). refund_amount and reason lack any semantic enhancement beyond the schema, so partial coverage.

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 creates a refund request using platform order_no/orderid, and distinguishes itself from sibling tools like query_refund_status by noting submission is not final. The verb-resource pairing is specific.

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?

Explicitly advises that mch_refund_no must be unique per refund and that successful submission only means accepted/processing, directing users to call query_refund_status to confirm. This provides clear when-to-use and follow-up guidance.

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