Refund an order after user confirmation. Specify amount in minor units for a partial refund; omit for a full refund.
Refund an order. Omit amount for a full refund; pass amount (minor units) for a partial refund. Only call after the user confirms.
| Name | Required | Description | Default |
|---|---|---|---|
| amount | No | Partial refund amount in minor units; omit for full refund | |
| orderId | No | ||
| reference | No | Refund reference / receipt id |
Changes observed during successful MCP inspections.
v0.73.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It mentions the confirmation requirement and partial/full refund semantics, but does not disclose side effects on order status, permission requirements, idempotency, or error conditions. This is a significant gap for a mutation 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 two sentences with no wasted words. The purpose is front-loaded, and the critical usage condition (confirmation) is stated clearly. It is efficient and well-structured.
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 the essential mechanics (full vs partial refund) and the confirmation prerequisite, but lacks information on expected response, side effects on order state, idempotency, or failure modes. For a tool with no output schema and no annotations, this leaves some ambiguity about what happens after the call succeeds.
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 the amount parameter (minor units, omit for full refund) and the reference parameter (refund reference). The schema already documents these but the description clarifies the conditional behavior. The orderId parameter is not described in either the schema or the description, but its purpose is self-evident. Schema coverage is 67%, so the description meaningfully compensates.
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 verb (refund) and resource (an order), and adds specificity by distinguishing full vs partial refunds. This differentiates it from sibling tools like cancel_order, which likely has a different purpose.
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 provides a clear timing guideline ('Only call after the user confirms') but does not discuss when to use this tool vs alternatives such as cancel_order or record_order_payment. It offers a contextual rule but no exclusionary guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.