ServiceTitan MCP

export_transfers

Read-onlyIdempotent

Read the incremental transfers feed for bulk synchronization. Continue with tokens until done; recent uncommitted changes can be included but may repeat.

Instructions

Read the incremental transfers export feed for bulk synchronization. Start with a date or omit from to start at the beginning of the feed, continue immediately with continueFrom while hasMore is true, and when false retain it and wait before polling again. includeRecentChanges may return records sooner but can repeat them.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`from`	No	Continuation token or date string for incremental export
`includeRecentChanges`	No	Include recent changes not yet committed

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

A4.7/5.0

Behavior5/5

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

The description reveals behavior beyond the annotations: incremental feed semantics, continuation-token polling, the hasMore loop, and the fact that includeRecentChanges can return duplicate records. This is exactly the kind of operational nuance that an agent needs to call the tool correctly and interpret results safely.

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 sentences carry a complete pagination algorithm without waste. The key start condition is front-loaded, and the tradeoff around includeRecentChanges is stated in a compact final clause.

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 declare read-only, idempotent, non-destructive behavior, the description covers everything needed: how to start, how to advance, when to stop, and how to handle the optional parameter's duplication risk. Nothing essential is missing for an agent to invoke this correctly.

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%, but the description adds value by explaining that omitting from starts at the beginning and that the continuation token should be passed along. It also clarifies that includeRecentChanges may return records sooner but at the cost of possible repeats. The only small gap is that 'continueFrom' is referenced as a concept rather than being explicitly tied to the 'from' parameter.

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 'Read the incremental transfers export feed for bulk synchronization,' which names a specific verb, resource (transfers), and intent. This clearly differentiates it from the many other export_* sibling tools by focusing on the transfers feed and its bulk-sync purpose.

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?

It provides explicit operational guidance: start with a date or omit from, continue with continueFrom while hasMore is true, retain the token when false and wait before polling again, and notes the tradeoff of includeRecentChanges. It does not explicitly mention when to prefer this over sibling export or list tools, but the feed-specific language makes the intended context clear.

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

Deploy Server