Refund all or part of a card charge to the customer by specifying charge ID, amount, and reason; Squidbrake can hold risky refunds for approval and audit.
Refund all or part of a card charge back to the customer.
| Name | Required | Description | Default |
|---|---|---|---|
| amount | Yes | ||
| reason | Yes | ||
| charge_id | Yes | ||
| justification | No | Why you are making this call, in one sentence. The person who approves it reads this; some calls need it. |
Changes observed during successful MCP inspections.
v0.13.0Input schema / properties / justificationAdded value: +{
+ "description": "Why you are making this call, in one sentence. The person who approves it reads this; some calls need it.",
+ "type": "string"
+}v0.3.8Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and largely drops it. For an irreversible financial mutation it says nothing about required permissions, whether refunds need approval, idempotency, time limits on how far back a charge can be refunded, or what happens on failure. The only behavioral hint is 'all or part', which implies partial refunds are supported.
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?
One front-loaded sentence with no filler and the key scope qualifier ('all or part') in place. It is efficiently written, though the terseness leaves no room for the operational detail this tool needs.
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?
For a 4-parameter, 3-required financial mutation with no annotations, no output schema, and 25% schema coverage, the description is well short of complete. It omits approval flow, permission requirements, refund limits, and error behavior, all of which an agent needs before invoking it.
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 coverage is only 25% (just 'justification' is documented), so the description must compensate, and it mostly does not. It implies 'amount' may be a partial value, but 'charge_id' and 'reason' get no added meaning such as accepted formats or valid reason values, and there are no enums to fall back on.
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 gives a specific verb ('Refund') and resource ('card charge') plus the scope 'all or part', which is enough to distinguish it from siblings like payments_transfer or payments_list_charges. It stops short of explicitly naming a sibling or contrasting itself with one, so it lands at 4 rather than 5.
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?
There is no statement of when to use this tool versus alternatives, no preconditions, and no mention of the approval workflow that the sibling tools (acme_check_approval, acme_ask_user) and the 'justification' parameter clearly imply. The agent is left to infer everything about context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.