Skip to main content
Glama
Pirate Ship MCP Server

Pirate Ship MCP Server

List refunds

list_refunds
Read-onlyIdempotent

Retrieve label refunds with status, amount, tracking and recipient, newest first; filter by request date, status or search to review pending, approved or declined refunds.

Instructions

Label refunds with their status and amount, newest request first.

The Reports, Refunds table: every label refund the account asked for (or Pirate Ship made automatically for an unused label), when it was requested, approved, declined or reversed, the tracking number, recipient and amount in US dollars. from_date and to_date narrow by the request day.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_refunds"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNoOrder by date.newest
limitNoRows per page, 1 to 100.
offsetNoRows to skip: the next page starts at offset + limit while it is below total.
searchNoFree text, as in the report's search box.
statusNoRefund status as the table shows it, e.g. Pending, Approved, Declined.
to_dateNoLast day, YYYY-MM-DD, included.
from_dateNoFirst day, YYYY-MM-DD, in your timezone.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.0.4
    • addedInput schema / properties / limit / description
      Added value: +"Rows per page, 1 to 100."
    • addedInput schema / properties / offset / description
      Added value: +"Rows to skip: the next page starts at offset + limit while it is below total."
    • addedInput schema / properties / sort / description
      Added value: +"Order by date."
  2. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description still adds real context the annotations lack: refunds may be customer-requested or auto-generated by Pirate Ship for an unused label, statuses include requested/approved/declined/reversed, and amounts are in USD.

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?

Two sentences, front-loaded with the core action before the detail. The second sentence is dense but each listed field (status, dates, tracking, recipient, amount) earns its place given there is no output schema.

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

Completeness4/5

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

With no output schema, the description usefully enumerates what a row contains — status lifecycle, request date, tracking number, recipient and USD amount — which is what an agent needs to interpret results. Pagination behaviour is left to the schema, which is acceptable since limit/offset are fully documented there.

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 coverage is 100%, so the schema already documents sort, limit, offset, search, status and the date fields. The only genuine addition is that from_date/to_date filter on the request day (not the approval or reversal day), which is useful but narrow; the 'newest first' phrasing merely restates the default sort.

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 description states a specific verb and resource ('label refunds' with status and amount, newest first), so an agent can tell it enumerates refund records. It does not differentiate from near neighbours like list_return_labels, list_receipts or list_transactions, leaving some ambiguity about which list tool to pick.

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?

Usage is only implied: the sentence about the Reports/Refunds table and the from_date/to_date narrowing suggests when to reach for it, and the parenthetical about Pirate Ship auto-refunds clarifies coverage. There is no explicit statement of when to use this versus list_return_labels or list_transactions, and no exclusions.

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