Podyx MCP

podyx_get_external_refund

Read-onlyIdempotent

Retrieve an external refund by UUID to check its current money and cancellation state for read-only verification and reconciliation.

Instructions

Get external refund GET /api/v2/external-refunds/{id}. Acceptance is an immutable delivery receipt. A refund request reserves a real outstanding obligation; only a studio report of actual success counts returned money. Studio refund UUIDs are independent from HTTP keys. Replacements explicitly name a failed or reversed attempt in the identical frozen scope and share its obligation. GET exposes current money and cancellation state. Recovery requires current key, tenant and owning-resource authority even after new commercial entry is disabled. Provider IDs are never accepted or manufactured. Read/preview only. Follow all pagination; a quote does not reserve a slot or lock a price.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "path": "<path>"
    },
    "name": "podyx_get_external_refund"
  }
}

Input Schema

Name	Required	Description	Default
`path`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.4.0Nov 7, 2026

TDQS

B3.2/5.0

Behavior4/5

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

The annotations already establish that this is a non-destructive, idempotent read operation. The description adds valuable behavioral context beyond that: recovery requires the current key, tenant, and owning-resource authority, and provider IDs are never accepted or manufactured. It also explains that the GET exposes current money and cancellation state, though the delivery is obscured by abstract refund-policy language.

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

Conciseness2/5

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

The description is a dense block of abstract business-policy sentences, several of which do not help an agent invoke this simple GET endpoint. Important invocation constraints such as 'Read/preview only' are buried rather than front-loaded. It is overlong and poorly structured for a one-parameter read tool.

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?

The tool itself is simple, and the annotations already cover its safety profile. However, with no output schema, the description should more clearly explain what the returned refund representation contains and should unmistakably document the single `id` parameter. It provides useful auth context and partial return-state information, but remains incomplete and confusing in key areas.

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 carry the burden for the single nested `path.id` parameter. It partly does so by framing the ID as a studio refund UUID and saying provider IDs are not accepted, but 'independent from HTTP keys' is ambiguous and the description does not clearly restate the expected UUID format or path structure. It adds some meaning but not enough to fully compensate for the schema gap.

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

Purpose4/5

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

The opening sentence names a specific verb and resource: 'Get external refund GET /api/v2/external-refunds/{id}'. This makes the tool distinguishable from sibling tools such as podyx_list_external_refund_collections. However, the surrounding domain jargon makes the core purpose less immediately obvious than it could be.

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

Usage Guidelines2/5

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

The description says 'Read/preview only' and 'Follow all pagination', but it does not clearly state when to use this tool versus the external refund collection/list sibling. There is no explicit guidance on when not to use it or how to obtain a valid refund ID. The usage guidance is mostly implied or buried in business-rule language.

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

Deploy Server