Skip to main content
Glama
@cmssy/mcp-server

@cmssy/mcp-server

Official

Get order

get_order
Read-only

Fetch full details for a single order by ID—items, totals, tax, payment and fulfillment status, refunds, invoices, parcels, returns, and custom fields—for order review and customer support.

Instructions

Get one order's full details by its id: items, the full money column (subtotal, discount, shipping, tax, total - all minor units), displayMode (net or gross, how the buyer read prices), taxRoundingMethod (per_line or per_rate), taxTreatment (kind standard, reverse_charge, exempt or export - goods shipped out of the EU VAT area, or from a seller outside the EU to another country, frozen at checkout with the facts it rests on: legalNote, the text to print on the invoice, null for standard; buyerVatId, buyerVatCountry and buyerVatVerifiedAt of the VAT id that decided it; sellerCountry; shipToCountry; orders placed before it was recorded read standard), removedTax (VAT taken out of gross-stored prices on a reverse_charge, exempt or export order, minor units, 0 otherwise; total = subtotal - discount + shippingTotal - removedTax), amounts (net, tax and gross of subtotal, discount, shipping and total), the frozen discount code, channel (the sales channel the order was placed through: id, key, name; null for none), priceList / priceListName (the primary price list the order was priced from, name frozen at checkout; null when none) and priceListSource (MEMBER, COMPANY or CHANNEL - whose list it was), pricingChain (the lists tried in order: buyer, channelDated, channelBase; each null when none) - every list reference carries deleted, true once that list was deleted after the order, and each item's priceListId / priceListSource name the list that priced that line, PO number, shipping address, payment/fulfillment status, amountPaid (collected so far), balanceDue (total - amountPaid, what the buyer still owes; a refund does not change it), refundedAmount (refunded so far across every refund, minor units; left to refund = amountPaid - refundedAmount), refundedAt (when the latest refund was recorded, null when none), refundReferences (the refund references recorded, oldest first - refund_order and refund_return ignore a reference already listed), invoices (every invoice recorded, oldest first: kind invoice - at most one, the order's invoice - then its corrections of kind correction, each with number, url, provider and issuedAt; record_order_invoice adds the invoice, record_order_invoice_correction a correction), and the parcels (shipments: id, carrier, tracking number and link, status, history) - a parcel's id is what update_shipment takes - the returns (id, number, status, lines with reason and received/restocked units, return-parcel tracking, refunded amount, history) - a return's id is what the *_return tools take - and customFields, the order's custom field values by key.

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": {
      "orderId": "<orderId>"
    },
    "name": "get_order"
  }
}

Input Schema

NameRequiredDescriptionDefault
orderIdYesThe order's id (from list_orders)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.73.2
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / required
      Added value: +[
      +  "orderId"
      +]
  2. First observedv0.73.1

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already establish readOnlyHint=true and destructiveHint=false, so safety is covered; the description instead adds substantial semantic behavior an agent could not infer: all money is in minor units, list names are frozen at checkout, deleted lists are flagged via a 'deleted' boolean, taxTreatment is frozen with the facts it rests on, and pre-recording orders read standard. It does not discuss authorization requirements or rate limits, but for a read tool the added data semantics are unusually rich.

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 purpose is correctly front-loaded in the first clause, but the remainder is one enormous run-on sentence dense with nested parentheticals covering VAT internals, pricing chains, refunds, invoices, parcels and returns. Almost every clause is substantive rather than filler, yet the lack of any list, headings or sentence breaks makes it hard to scan and pushes critical routing hints into the middle of the wall of text.

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?

No output schema exists, so the description must carry return-shape information, and it does so exhaustively: money columns, amounts breakdown, tax fields, pricing chain, invoices, parcels, returns and custom fields. Combined with a single well-documented required parameter and read-only annotations, an agent has enough to call it correctly and interpret the response, though the completeness is achieved at the cost of readability.

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?

There is a single parameter with 100% schema description coverage, and the schema already says 'The order's id (from list_orders)'. The description adds only 'by its id', so it contributes no format, example, or sourcing detail beyond the structured field; baseline 3 applies when the schema does the work.

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 clause 'Get one order's full details by its id' states a specific verb (get), resource (one order) and scope (full details), so an agent can tell it fetches a single record rather than a list. It never explicitly contrasts itself with siblings such as get_order_pipeline or list_orders, so sibling differentiation is left to inference.

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 by 'one order ... by its id' plus the parenthetical '(from list_orders)' in the schema, which hints the discovery path. There is no explicit when-to-use versus get_order_pipeline or when-not guidance. It does scatter useful cross-tool routing hints (a parcel id is what update_shipment takes, a return id is what *_return tools take, refund_order ignores already-listed references), but these are buried in the payload enumeration rather than framed as invocation guidance.

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

Deploy Server

Other Tools