Skip to main content
Glama

Field Service Business Platform by Doing Work

invoices_refund

Refund part or all of a payment (owner or office, or their agent). The refund shows up once the processor confirms it. An agent refund above the shop's agent refund cap (shops.setAgentMoney, $250 unless the owner changed it) does not run: it waits for the owner's OK and the reply says approval_required.

Input Schema

NameRequiredDescriptionDefault
charge_idYes
amount_minorYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses asynchronous confirmation ('shows up once the processor confirms it'), a permission gate with a configurable $250 default cap referencing shops.setAgentMoney, and the exact reply signal 'approval_required' when the refund is held. It omits idempotency behavior and what a successful response contains, so it is not exhaustive.

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

Conciseness4/5

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

Three sentences, verb and scope front-loaded, with no filler. The approval-cap parenthetical is dense but every clause adds operational information.

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

Completeness5/5

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

For a two-parameter mutation with no annotations and no output schema, the description supplies the three things an agent actually needs: who is authorized, the timing of the effect, and the approval-required outcome. Nothing essential is missing for correct invocation.

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 description coverage is 0%, so the description must compensate for two undocumented parameters. 'Refund part or all of a payment' implies amount_minor is the refund amount and that partial amounts are legal, but it never says the value is in minor units or that charge_id refers to the original charge being refunded. Partial compensation only.

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?

The description opens with a specific verb and resource ('Refund part or all of a payment') and bounds the scope to partial or full amounts. An agent can distinguish this from invoices_void or invoices_markPaidOutside without consulting any schema.

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?

It names who may call it (owner, office, or their agent) and states precisely the condition under which the call will not execute: an agent refund above the shop's agent refund cap. It does not contrast against sibling operations like voiding an invoice, so it stops short of full alternative routing.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources