ServiceTitan MCP

crm_customers_list

Read-onlyIdempotent

Locate customer records by searching IDs, name, address, phone, coordinates, external data, or date ranges. Returns one page of matching results.

Instructions

Search customers by IDs, name, address, phone, coordinates, external data, activity, or created and modified ranges. Returns one page; use crm_customers_get for a known ID.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`ids`	No	Comma-delimited customer IDs
`zip`	No	Filter by zip
`city`	No	Filter by city
`name`	No	Filter by name
`page`	No	Page number (starts at 1)
`sort`	No	Sort: Field (default), +Field (asc), or -Field (desc). Fields: Id, ModifiedOn, CreatedOn
`unit`	No	Filter by unit
`phone`	No	Filter by contact phone
`state`	No	Filter by state
`active`	No	Filter by active status	True
`street`	No	Filter by street
`country`	No	Filter by country
`latitude`	No	Filter by latitude
`pageSize`	No	Records per page (default 50)
`longitude`	No	Filter by longitude
`includeTotal`	No	Include total count in response
`createdBefore`	No
`modifiedBefore`	No
`externalDataKey`	No	External data key
`createdOnOrAfter`	No
`modifiedOnOrAfter`	No
`externalDataValues`	No	External data values
`externalDataApplicationGuid`	No	External data application GUID
`excludeAccountingChangesFromModifiedDateRange`	No	Exclude accounting-only changes from modified date filters

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv3.0.0Sep 6, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {},
+  "type": "object"
+}

First observedv2.5.1Apr 18, 2026

TDQS

A4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context by noting pagination ('Returns one page') and the distinction from a direct get, but it does not disclose other behavior such as defaults or response structure, which is partly covered by the output schema.

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?

Two short sentences, front-loaded with the tool's purpose and followed by direct routing guidance. Every clause earns its place; no filler or redundancy.

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 24-parameter search tool with an output schema and strong annotations, the description gives enough orientation: it summarizes searchable dimensions, clarifies pagination, and points to the right sibling for known IDs. It does not mention sorting or defaults, but those are already specified in the input schema.

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 83%, so the schema already documents most parameters. The description adds a useful high-level grouping of filter categories, especially covering the otherwise undocumented date-range parameters as 'created and modified ranges,' but it does not deepen individual parameter semantics beyond the schema.

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?

The description states the specific verb 'Search customers' and enumerates the key search dimensions (IDs, name, address, phone, coordinates, external data, activity, created/modified ranges). It also distinguishes itself from crm_customers_get by noting this tool returns a page and should be used for search rather than known-ID lookup.

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?

The description explicitly says 'Returns one page' and tells the agent to use crm_customers_get for a known ID, which is clear routing guidance. It does not mention bulk-export alternatives like export_customers, but the one-page statement plus sibling context is enough for most selection decisions.

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

Deploy Server