ServiceTitan MCP

intel_labor_cost

Read-onlyIdempotent

Summarize employee regular, overtime, and total hours for a date range, and derive labor cost and effective hourly rate when gross pay data is available.

Instructions

Summarize employee regular, overtime, double-overtime, and total hours from Report 166 for the selected date range. When the tenant report exposes GrossPay, the tool also derives cost and effective hourly rate; otherwise those fields are unavailable rather than estimated. Report execution may wait for per-report/client spacing, and source failures are returned in _warnings.

Examples:

"What labor hours were reported this month?" -> startDate="2026-03-01", endDate="2026-04-01"
"Show overtime hours by employee for Q1" -> startDate="2026-01-01", endDate="2026-04-01"

Input Schema

TableJSON Schema

Name	Required	Description
`endDate`	Yes	End date (YYYY-MM-DD)
`startDate`	Yes	Start date (YYYY-MM-DD)
`technicianId`	No	Filter by technician ID
`businessUnitId`	No	Filter by business unit ID
`technicianName`	No	Filter by technician name (resolved via cache, e.g. 'John'). Alternative to technicianId.
`businessUnitName`	No	Filter by business unit name (resolved via cache, e.g. 'HVAC'). Alternative to businessUnitId.

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

A4.6/5.0

Behavior5/5

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

Beyond the annotations, the description discloses valuable behaviors: cost fields depend on whether the tenant report exposes GrossPay, fields are 'unavailable rather than estimated,' execution may wait for report/client spacing, and source failures surface in _warnings. This gives the agent realistic expectations that annotations alone could not.

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 tightly structured: core purpose first, conditional behavior second, execution/warning caveats third, then two useful examples. Every sentence earns its place, and the examples are compact rather than redundant.

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?

The description covers the source report, conditional derivation behavior, execution wait time, and warning conventions. An output schema exists, so return fields do not need to be spelled out. It does not directly discuss optional filters or grouping shape, but the schema descriptions and examples largely compensate.

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 the schema already documents all six parameters. The description adds value by demonstrating date-range semantics through examples (month and Q1 boundaries), which clarifies that endDate acts as an exclusive bound. This is meaningful enrichment beyond the schema's basic YYYY-MM-DD 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?

The description states a specific verb ('Summarize'), a specific source ('Report 166'), and the exact metrics covered (regular, overtime, double-overtime, total hours). It also clarifies when cost/effective hourly rate are derived versus unavailable, which distinguishes it from raw payroll list tools.

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 examples give concrete natural-language-to-parameter mappings ('What labor hours were reported this month?' -> startDate/endDate), which gives an agent clear context for when to invoke it. However, it never explicitly names an alternative tool or states when not to use this tool, so it misses the highest bar.

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

Deploy Server