request_commerce_refundCreate a durable buyer refund request for a paid dynamic purchase. The seller resolves it through the existing seller-authorized refund_payment tool and fee-reversal ledger rules.
| Name | Required | Description | Default |
|---|---|---|---|
| reason | Yes | ||
| purchaseId | Yes | ||
| amountMinor | Yes | ||
| idempotencyKey | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only indicate a non-read-only, non-destructive mutation. The description adds meaningful behavioral context: the request is durable, the seller must resolve it, and fee-reversal ledger rules apply. It does not cover authentication or idempotency behavior, but it does not contradict the annotations.
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 focused sentences with no wasted words. It front-loads the core action and uses the second sentence to clarify the downstream resolution process.
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 is adequate for tool selection but thin for invocation: it does not describe the success response, idempotency semantics, or how the fee-reversal rules affect the request. With no output schema and no parameter documentation, an agent would need to infer several invocation details.
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 description coverage is 0%, and the description does not explain the four required parameters. It mentions a 'paid dynamic purchase' as context for purchaseId, but it gives no meaning for amountMinor, reason, or idempotencyKey beyond what their names suggest.
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 uses a specific verb ('Create') and identifies the exact resource: a durable buyer refund request for a paid dynamic purchase. It also implicitly distinguishes itself from the seller-side refund_payment tool by explaining who resolves the request.
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 gives clear context by routing the buyer's request to this tool and the seller's resolution to refund_payment, which is the most relevant sibling. It does not explicitly enumerate all alternatives or state a crisp 'use this when...' rule, so it stops short of a 5.
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.
The set has multiple near-synonymous read and recovery surfaces, e.g. get_commerce_purchase_status vs get_purchase_recovery_status vs recover_authorized_purchase vs recover_commerce_purchase, and discover_assurance_services vs discover_commerce_index vs get_discovery_manifest vs search_verified_offers. Long descriptions are required to tell them apart, so misselection is likely.
All names follow a readable snake_case verb_noun pattern, with get_, request_, create_, verify_, and recover_ prefixes used consistently. The main deviation is read operations split across get_/discover_/inspect_/search_/list_, which is still understandable but not perfectly uniform.
At 50 tools this is in the extreme-mismatch band for an MCP server. Even with a broad payment/commerce/discovery domain, dozens of get/status/recovery tools could be consolidated or parameterized.
The toolset covers the major lifecycles: registration, wallet, funding, payment, commerce offer/purchase/fulfillment/refund, mandates, and verification. Minor gaps such as no service unregister/update, no payment-request cancellation, and no wallet deletion are workable but not fatal.