shopware-mcp

Search customers

customers_search

Read-onlyIdempotent

Search customers by name, email, customer number, or filters and get compact summaries with group, order count, and last order date.

Instructions

Search customers by term (name, email, customer number) and/or Criteria filters such as email, active, guest, group.name or lastOrderDate ranges. Returns compact summaries with group, order count and last order date. Use customers_get for addresses and payment method. Returns { total, page, limit, items[] }.

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": "customers_search"
  }
}

Input Schema

Name	Required	Description
`page`	No	1-based page
`sort`	No	Sort order; defaults per tool
`term`	No	Full-text search term
`limit`	No	Items per page, max 50 (default from SHOPWARE_MCP_DEFAULT_LIMIT)
`fields`	No	Extra raw entity fields to add to each item, e.g. ['customFields', 'ean']. Dot-paths allowed.
`filter`	No	Criteria filters, combined with AND

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.11.1Nov 6, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds value beyond them by disclosing the result shape ({ total, page, limit, items[] }) and that items are compact summaries with group, order count and last order date — which tells the agent it must call customers_get for detail fields.

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

Conciseness5/5

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

Three short sentences, front-loaded with the search capability, then the sibling routing, then the return shape. No redundant or filler phrasing.

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 correctly spells out the response envelope and summary fields, and covers the searchable surface and the fallback tool. Minor gap: combination semantics (AND) and paging/sort are left entirely to the schema, though that is low-risk.

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?

Schema coverage is 100%, so baseline is 3. The description goes beyond the schema by naming concrete filter fields (email, active, guest, group.name, lastOrderDate ranges) and the three term-searchable attributes, giving the agent usable example values rather than abstract Criteria descriptions.

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?

States a specific verb (search) and resource (customers), enumerates what the term searches over (name, email, customer number) and what the filter path can express. It is immediately distinguishable from customers_get and orders_search.

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

Usage Guidelines4/5

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

Explicitly routes one adjacent need to a sibling: 'Use customers_get for addresses and payment method.' It also implies term-search vs criteria-filter selection. It stops short of stating when not to search at all (e.g. for a known ID), so it is clear but not fully exhaustive.

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