ServiceTitan MCP

intel_revenue_summary

Read-onlyIdempotent

Summarizes revenue and sales metrics for a selected date range, optionally filtered by business unit. Returns revenue, opportunities, conversion, and sales totals to answer performance questions.

Instructions

Summarize Report 175 revenue and Report 179 sales for the selected date range, optionally filtered to one business unit. Returns completed, non-job, adjustment, and total revenue plus opportunities, conversion, and sales metrics by business unit; the aggregate reflects returned report rows and is not certified as an all-company total or as matching every tenant dashboard configuration. includeProductivityMetrics adds Report 177 metrics, and includeCollections fetches all payment pages for the period. Report calls are cached briefly and serialized per report/client with at least 65 seconds between starts; a failed source is identified in _warnings and its affected metrics may be empty.

Examples:

"What was our total revenue last month?" -> startDate="2026-02-01", endDate="2026-03-01"
"How much did HVAC bring in this quarter?" -> startDate="2026-01-01", endDate="2026-04-01", businessUnitName="HVAC"
"Revenue year to date" -> startDate="2026-01-01", endDate="2026-03-10"

Input Schema

TableJSON Schema

Name	Required	Description
`endDate`	Yes	End date (YYYY-MM-DD)
`startDate`	Yes	Start date (YYYY-MM-DD)
`businessUnitId`	No	Filter by business unit ID
`businessUnitName`	No	Filter by business unit name (resolved via cache, e.g. 'HVAC'). Alternative to businessUnitId.
`includeCollections`	No	Include payments received during the selected period. Default: false.
`includeProductivityMetrics`	No	Include business-unit productivity metrics from Report 177: revenue per hour, billable efficiency, upsold work, tasks per opportunity, and recalls. Default: false.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv3.0.1Sep 6, 2026

changedInput schema / properties / includeProductivityMetrics / description

Previous value: -"Include BU-level productivity metrics (Report 177: rev/hr, billable efficiency, upsold, tasks/opp, recalls). Adds ~0.5-1s latency. Default: false."New value: +"Include business-unit productivity metrics from Report 177: revenue per hour, billable efficiency, upsold work, tasks per opportunity, and recalls. Default: false."

Changed2 schema fields changedv3.0.0Sep 6, 2026

changedInput schema / properties / includeCollections / description

Previous value: -"Include payment/collections data (totalCollected, outstanding). Adds ~20s latency due to payment pagination. Default: false."New value: +"Include payments received during the selected period. Default: false."

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

A4.7/5.0

Behavior5/5

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

Annotations already mark the tool as read-only, idempotent, and non-destructive, and the description adds substantial behavioral context: aggregate totals are not certified as all-company figures, calls are cached and serialized with a 65-second gap, failures surface in _warnings, and affected metrics may be empty. This goes well beyond the annotation baseline.

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 dense but every sentence earns its place: main purpose, return-metric summary, caveat about aggregate certification, optional feature explanations, caching/failure behavior, and practical examples. It is front-loaded with the core purpose and uses examples to anchor parameter usage.

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 output schema exists and the annotations cover safety, the description is complete: it names source reports, metric categories, optional filters, failure behavior, caching semantics, and provides runnable examples. An agent has enough to select and invoke the tool correctly without significant gaps.

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?

The input schema covers 100% of parameters, so the baseline is 3, but the description adds value by clarifying includeProductivityMetrics adds Report 177 metrics, includeCollections fetches all payment pages, and businessUnitName supports natural-language filters like 'HVAC'. The examples also give concrete date-format usage for startDate and endDate.

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 opens with a specific verb and resource: 'Summarize Report 175 revenue and Report 179 sales...' and clearly states the optional business-unit filter. It also distinguishes the tool from the many intel_* siblings by naming exact reports and metric groups, so an agent can tell what this tool does without opening schemas.

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 gives clear context for when to use the tool through natural-language examples mapping to date ranges and an optional business unit. It does not explicitly name alternatives or exclusion conditions, but the examples and report-specific language provide enough guidance for typical revenue-summary queries.

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

Deploy Server