Field Service Business Platform by Doing Work

imports_historyPreview

Dry run of a history import (kind jobs, quotes, invoices, pricebook, equipment, maintenance_plans, payments or flat_rate). Writes nothing. Returns a suggested mapping, what each record would do (create, update, skip, skip_blank, skip_closed or error) with how its customer matched, and a preview_hash. Show it to the owner; imports.historyRun needs the same hash.

Input Schema

Name	Required	Description
`csv`	Yes
`kind`	Yes
`preset`	No
`source`	No	Where the file came from, like jobber or housecall_pro. Old ids are remembered per source. Defaults to the preset, or csv.
`mapping`	No
`shop_id`	Yes
`on_match`	No	What to do with a record already imported (same old id) or already in Doing Work. skip (default) leaves it as it is; update refreshes jobs (summary, status, new visits) and price book items. Quotes and invoices are never changed after import.
`plans_as`	No	maintenance_plans only. reminders (default): service due reminders, no money. billed: real maintenance plans at the price per term in the file, which the owner confirms in the preview. Each plan's next invoice is made on its next due date and is not sent on its own (auto_send off).
`equipment_kind`	No	equipment kind only: the type for every row when the file has no type column, like Furnace for a Jobber custom field "Furnace Model". Guessed from the column names when left out; the preview returns it.

Output Schema

Name	Required	Description	Default
`kind`	Yes
`skip`	Yes
`items`	Yes
`create`	Yes
`failed`	Yes
`source`	Yes
`update`	Yes
`headers`	Yes
`mapping`	Yes
`records`	Yes
`on_match`	Yes
`row_errors`	Yes
`skip_closed`	Yes
`preview_hash`	Yes
`equipment_kind`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedNov 2, 2026

addedInput schema / properties / equipment_kind

Added value: +{
+  "description": "equipment kind only: the type for every row when the file has no type column, like Furnace for a Jobber custom field \"Furnace Model\". Guessed from the column names when left out; the preview returns it.",
+  "maxLength": 100,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / plans_as

Added value: +{
+  "description": "maintenance_plans only. reminders (default): service due reminders, no money. billed: real maintenance plans at the price per term in the file, which the owner confirms in the preview. Each plan's next invoice is made on its next due date and is not sent on its own (auto_send off).",
+  "enum": [
+    "reminders",
+    "billed"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / equipment_kind

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

changedOutput schema / required

Previous value: -[
-  "kind",
-  "source",
-  "on_match",
-  "headers",
-  "mapping",
-  "preview_hash",
-  "records",
-  "create",
-  "update",
-  "skip",
-  "skip_closed",
-  "failed",
-  "row_errors",
-  "items"
-]New value: +[
+  "kind",
+  "source",
+  "on_match",
+  "equipment_kind",
+  "headers",
+  "mapping",
+  "preview_hash",
+  "records",
+  "create",
+  "update",
+  "skip",
+  "skip_closed",
+  "failed",
+  "row_errors",
+  "items"
+]

First observedNov 1, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the no-write guarantee, the returned mapping, the per-record outcome vocabulary (create/update/skip/skip_blank/skip_closed/error), customer-match reporting, and the preview_hash requirement. It omits rate/size limits on the CSV and whether errors in one row abort the whole preview.

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?

Three dense sentences, front-loaded with the dry-run nature and the safety guarantee before the return payload and the follow-up call. The parenthetical kind list is a little long but earns its place by bounding scope.

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 an output schema exists, the description needn't detail the response, yet it still names the key artifacts an agent must chain forward (mapping, per-record action, preview_hash). What's missing is the setup context an importer needs — prerequisites for obtaining a usable CSV and how mapping/preset interplay — leaving a small gap for a nine-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 44%, yet the description adds nothing about parameters beyond restating the kind enum. Undocumented-or-thin parameters like preset, mapping, source and the interaction between preset and mapping are left entirely to the schema, so it does not compensate for the coverage gap.

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?

Opens with a specific verb and resource ('Dry run of a history import') and enumerates the supported kinds, immediately separating it from imports_historyRun, imports_preview and imports_fields. An agent can place it in the import workflow without opening the schema.

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 pairing with imports.historyRun and the instruction to show results to the owner make the call sequence explicit, and 'Writes nothing' signals it is safe to call first. It does not, however, contrast with sibling imports_preview for non-history data, so the agent must infer which import family to use.

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

All Field Service Business Platform by Doing Work tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?