ServiceTitan MCP

intel_campaign_performance

Read-onlyIdempotent

Compare marketing campaign performance across calls, bookings, revenue, and conversion for any date range. Narrow results to a single campaign with campaignId, or review all campaigns to identify which are driving results.

Instructions

Compare marketing campaigns over the selected date range by combining all fetched call, booking, job, and invoice pages. Returns calls, bookings, booked-call conversion, attributed revenue, and revenue per call; campaignId narrows the analysis to one known campaign. The metrics reflect the wrapper's cross-source attribution logic, and partial source failures are returned in _warnings.

Examples:

"Which marketing campaigns are working?" -> startDate="2026-01-01", endDate="2026-03-10"
"How many calls are we getting from Google Ads?" -> startDate="2026-01-01", endDate="2026-03-10", campaignId=
"What's our call-to-booking rate?" -> startDate="2026-01-01", endDate="2026-03-10"

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Max campaigns to analyze (default 20, max 50).
`endDate`	Yes	End date (YYYY-MM-DD)
`startDate`	Yes	Start date (YYYY-MM-DD)
`campaignId`	No	Single campaign (omit for all)

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

A4.1/5.0

Behavior4/5

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

The description adds meaningful behavior beyond the readOnly/idempotent annotations: it combines all fetched call, booking, job, and invoice pages, relies on the wrapper's cross-source attribution logic, and reports partial source failures in _warnings. This is useful operational context that the annotations alone do not convey.

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?

The description is efficiently front-loaded with purpose, outputs, and key behavioral caveats, followed by three illustrative examples. The examples are relevant and earned; only minor redundancy exists between the prose and examples.

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?

Given the output schema is present and all parameters are documented in the input schema, the description covers the important non-schema context: attribution behavior, warning reporting, campaign filtering, and use-case examples. It is adequately complete for an analytics wrapper tool.

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 coverage is 100%, so the baseline is 3. The description adds value for campaignId by explaining it 'narrows the analysis to one known campaign' and demonstrates startDate/endDate usage in examples, but does not add substantial semantics beyond the schema's own 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?

Description opens with a specific action and resource: 'Compare marketing campaigns over the selected date range' and enumerates concrete outputs (calls, bookings, conversion, attributed revenue, revenue per call). It clearly distinguishes this from raw marketing list endpoints and from other intel_* analytics siblings by focusing on campaign-level comparison with cross-source attribution.

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 natural-language examples provide clear contexts: campaign comparison, source-specific call volume, and call-to-booking rate. There is no explicit statement of when not to use it or which alternative to choose, but the examples and 'campaignId narrows the analysis' give strong implied usage guidance.

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

Deploy Server