ServiceTitan MCP

dispatch_jobs_list

Read-onlyIdempotent

Find jobs in ServiceTitan by filtering on IDs, customer, location, status, appointments, equipment, tags, or dates. Returns paged results to locate the records you need.

Instructions

Search jobs by IDs, number, customer, location, project, status, appointments, equipment, tags, dates, or other supported filters. Returns one page; use dispatch_jobs_get for a known job ID.

Input Schema

TableJSON Schema

Name	Required	Description
`ids`	No	Comma-separated job IDs (maximum 50)
`page`	No	Page number (starts at 1)
`sort`	No	Sort: Field (default), +Field (asc), or -Field (desc). Fields: Id, ModifiedOn, CreatedOn, Priority
`number`	No	Filter by job number
`pageSize`	No	Records per page (default 50)
`priority`	No	Job priority filter
`soldById`	No	Filter by selling technician ID
`bookingId`	No	Filter by booking ID
`invoiceId`	No	Filter by invoice ID
`jobStatus`	No	Job status filter
`jobTypeId`	No	Filter by job type ID
`projectId`	No	Filter by project ID
`campaignId`	No	Filter by campaign ID
`customerId`	No	Filter by customer ID
`locationId`	No	Filter by location ID
`tagTypeIds`	No	Comma-separated tag type IDs
`equipmentIds`	No	Comma-separated installed equipment IDs; returns jobs with at least one attached equipment item
`includeTotal`	No	Include total count in response
`technicianId`	No	Filter by technician ID
`createdBefore`	No	Return items created before this UTC timestamp
`businessUnitId`	No	Filter by business unit ID
`modifiedBefore`	No	Return items modified before this UTC timestamp
`completedBefore`	No	Return jobs completed before this UTC timestamp
`externalDataKey`	No	External data key
`createdOnOrAfter`	No	Return items created on or after this UTC timestamp
`appointmentStatus`	No	Appointment status filter
`modifiedOnOrAfter`	No	Return items modified on or after this UTC timestamp
`completedOnOrAfter`	No	Return jobs completed on or after this UTC timestamp
`externalDataValues`	No	External data values (comma-separated, maximum 50)
`hasUnusedAppointments`	No	Return jobs with unused appointments
`appointmentStartsBefore`	No	Return jobs with any appointment before this UTC timestamp
`appointmentStartsOnOrAfter`	No	Return jobs with any appointment on or after this UTC timestamp
`externalDataApplicationGuid`	No	External data application GUID
`firstAppointmentStartsBefore`	No	Return jobs whose first appointment starts before this UTC timestamp
`firstAppointmentStartsOnOrAfter`	No	Return jobs whose first appointment starts on or after this UTC timestamp

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"
+}

Changed1 schema field changedv2.6.0Jun 17, 2026

addedInput schema / properties / equipmentIds

Added value: +{
+  "description": "Comma-separated installed equipment IDs; returns jobs with at least one attached equipment item",
+  "type": "string"
+}

First observedv2.5.1Apr 18, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive, and open-world behavior, so the bar is lower. The description adds useful behavioral context by stating that the operation 'Returns one page' and noting that other supported filters exist, which aligns with the openWorldHint. No contradiction exists.

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?

The description is two sentences with no filler. It front-loads the resource and filter scope, then adds the pagination note and the alternative tool for known IDs.

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

Completeness5/5

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

Given the full parameter schema, annotations, and output schema, the description is complete enough for an agent to correctly select and invoke the tool. It covers what the tool searches, the pagination behavior, and the correct sibling for single-record lookups.

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?

The input schema has 100% coverage with individual descriptions for all 35 parameters, so the description does not need to compensate. It provides a helpful categorical summary of filter types, but it does not add new semantic meaning or syntax beyond what the schema already gives.

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 uses a specific verb and resource: 'Search jobs,' and enumerates the main filter dimensions (IDs, number, customer, location, project, status, appointments, equipment, tags, dates). It also explicitly distinguishes itself from dispatch_jobs_get, which is for retrieving a known job ID.

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 clearly says to use dispatch_jobs_get when a known job ID is available and signals this is the paginated search variant with 'Returns one page.' It does not mention the bulk-export alternative like export_jobs, so the guidance is good but not exhaustive across all sibling tools.

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

Deploy Server