Skip to main content
Glama

refund

Process refunds for completed payments using correlation IDs to reverse transactions through the Junto MCP server's multi-provider payment system.

Instructions

Refund a completed payment by correlation ID.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesCorrelation ID of the payment to refund
providerNoProvider that handled the transaction

Implementation Reference

  • The handler for the 'refund' MCP tool, which calls the selected provider's refund method and performs auditing.
    server.tool(
      "refund",
      "Refund a completed payment by correlation ID.",
      RefundSchema.shape,
      async (params) => {
        try {
          const provider = pickProvider(undefined, undefined, params.provider);
          const result = await provider.refund(params.id);
    
          guardrails.audit({
            timestamp: new Date().toISOString(),
            type: "payment",
            action: "refund",
            tool: "refund",
            provider: provider.name,
            status: "executed",
          });
    
          return jsonResult(result);
        } catch (err) {
          guardrails.audit({
            timestamp: new Date().toISOString(),
            type: "payment",
            action: "refund",
            tool: "refund",
            status: "failed",
            reason: formatError(err),
          });
          return textResult(`Refund failed: ${formatError(err)}`);
        }
      }
    );
  • The schema definition for the 'refund' tool, requiring an ID and optional provider.
    const RefundSchema = z.object({
      id: z.string().describe("Correlation ID of the payment to refund"),
      provider: z.string().optional().describe("Provider that handled the transaction"),
    });
Behavior2/5

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

No annotations provided, so description carries full burden. States the operation is a refund on completed payments, but lacks critical details: idempotency, failure modes, partial vs full refunds, or synchronous/asynchronous behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single 7-word sentence with zero redundancy. Action verb front-loaded. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

High-stakes financial mutation tool with no annotations, no output schema, and minimal behavioral description. Inadequate for the operational complexity and risk level.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% description coverage. Description mentions 'correlation ID' reinforcing the id parameter, but adds no semantic value for the optional 'provider' parameter or usage scenarios beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clear specific verb 'Refund' and resource 'completed payment', clearly distinguishes from sibling tools like 'charge' or 'pay' which create payments rather than reverse them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies usage restriction via 'completed payment' (suggesting not for pending transactions), but lacks explicit when-to-use guidance or comparison to sibling alternatives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/vrllrv/junto-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server