Skip to main content
Glama

shopify_update_order

Destructive

Updates a Shopify order's note, email, phone, PO number, custom attributes, shipping address, and tags, with a dry-run preview before applying changes.

Instructions

Update order note, email, phone, PO number, additional details (customAttributes), shipping address and tags (orderUpdate). dryRun:true (the default) returns the current order and the change without applying it; dryRun:false applies it and returns before and after. Tags: addTags and removeTags change only the named tags; replaceTags replaces all tags. Requires write_orders.

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": {
      "store": "<store>",
      "id": "<id>"
    },
    "name": "shopify_update_order"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes
noteNo
emailNo
phoneNo
storeYes
dryRunNoTrue (the default) returns a before/after preview without changing anything in Shopify. Pass false to apply the change; the tool then reads the result back.
addTagsNoTags to add (tagsAdd). Other tags are kept.
poNumberNo
removeTagsNoTags to remove (tagsRemove). Other tags are kept.
replaceTagsNoReplaces all tags: every current tag not in this list is removed. Prefer addTags or removeTags.
shippingAddressNo
customAttributesNoReplaces the order's additional details (note attributes).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv2.2.0
    • addedInput schema / properties / customAttributes
      Added value: +{
      +  "description": "Replaces the order's additional details (note attributes).",
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "key": {
      +        "maxLength": 255,
      +        "minLength": 1,
      +        "type": "string"
      +      },
      +      "value": {
      +        "maxLength": 5000,
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "key",
      +      "value"
      +    ],
      +    "type": "object"
      +  },
      +  "maxItems": 100,
      +  "type": "array"
      +}
    • addedInput schema / properties / phone
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 40,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ]
      +}
    • addedInput schema / properties / poNumber
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 255,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ]
      +}
  2. Addedv2.0.1

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and non-idempotent, and the description adds real context beyond them: the write_orders scope prerequisite, the default-preview vs apply split, and the before/after return shape for real writes. The gap is that it doesn't say whether omitted fields are left untouched or whether shippingAddress merges vs replaces, which matters for a destructive mutation.

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?

Front-loads the field inventory, then the dryRun behavior, then tag semantics and scope in a tight, information-dense block with no filler. It does restate tag mechanics already present in the schema descriptions and compresses everything into two long sentences, slightly hurting scannability.

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?

For a 12-param destructive mutation with no output schema, it covers the essentials: what changes, the safe preview default, what a real run returns, the required scope, and tag-array interaction rules. Partial-update semantics for unmentioned fields and error/prerequisite behavior are the remaining holes.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 42% schema description coverage across 12 params, the description does compensating work: it clarifies dryRun's default and return behavior, defines addTags/removeTags as additive/subtractive versus replaceTags as wholesale, and notes customAttributes replaces the order's note attributes. store and id are never explained, and merge-vs-replace semantics for shippingAddress stay unstated.

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?

Names a specific verb (update) plus resource (order) and enumerates the exact field groups it touches: note, email, phone, PO number, customAttributes, shipping address, tags. The inventory of updatable fields makes it unmistakable against sibling tools such as shopify_update_product or shopify_update_customer.

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?

Provides useful operational guidance ('dryRun:true (the default)... dryRun:false applies it', 'Prefer addTags/removeTags' over replaceTags, 'Requires write_orders'), which tells the agent how to call it safely. It never states when to reach for this tool versus an alternative path, so usage guidance remains implied rather than explicit.

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