Skip to main content
Glama
zenskar

Zenskar MCP Server

Official
by zenskar

refundPayment

refundPayment

Issue a full or partial payment refund, specifying amount, destination (original method or credits), and whether to write off linked invoices.

Instructions

Refund a payment (full or partial). Pass refund_amount=0 (or full original amount) for a full refund, or a smaller positive integer for a partial refund. refund_destination + writeoff_invoices control where the refund money goes and whether linked invoices are written off. Host enforces user confirmation via the approval gate; do NOT ask the user to re-confirm before calling.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paymentIdYesThe unique identifier (UUID) of the payment to refund.
refund_amountYesRefund amount in the smallest currency unit (integer cents/paise). Use 0 to refund the full payment, or a positive integer for a partial refund. Must not exceed the payment's remaining refundable amount.
refund_destinationYesWhere to send the refund. Valid values: 'original_payment_method' (refund back to the source card/bank), 'credits' (issue customer credits instead of returning money).
writeoff_invoicesYesIf true, the invoice(s) linked to this payment are marked written off (no further collection). Set false to leave invoice balance owing after refund.
__userContextNoInternal user context for multi-tenant authentication and approval workflow
Behavior4/5

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

No annotations provided, so description carries full burden. It discloses that refund_destination and writeoff_invoices control where money goes and invoice write-off, and mentions host enforcement of confirmation. Lacks details on auth requirements or error behavior but sufficient for core 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?

Three sentences, front-loaded with purpose, no redundant information. Each sentence serves a clear role: purpose, refund logic, additional controls and confirmation note.

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

Completeness3/5

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

Covers core refund logic well but lacks description of return values or output. Since no output schema, description should hint at what the tool returns (e.g., refund confirmation). Missing error conditions or prerequisites like payment capture status.

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

Parameters4/5

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

Schema description coverage is 100%. Description adds value beyond schema: explains refund_amount=0 for full refund, clarifies refund_destination valid values, and writeoff_invoices effect. Provides useful context not in schema.

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?

Description clearly states the tool's purpose: 'Refund a payment (full or partial).' It is specific about the resource (payment) and action (refund), and distinguishes from siblings like payInvoice or createPayment.

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

Usage Guidelines4/5

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

Explicitly explains when to use full vs partial refund via refund_amount=0 or positive integer. Also instructs not to ask for user re-confirmation because host enforces approval. Does not explicitly contrast with alternative tools but provides clear context.

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/zenskar/mcp-zenskar'

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