Skip to main content
Glama

QuBe Sync: QuickBooks Desktop API for developers

Find txn deleteds

find_txn_deleteds
Read-onlyIdempotent

Lists the transactions deleted in the last 90 days, of the types txn_del_type names and no others: a deleted payment isn't listed when txn_del_type names only invoice and sales_order (observed on QuickBooks Enterprise 24.0, 2026-10-10), so name every type your app keeps. Each comes back with its type, id, reference number and when it was created and deleted, grouped by type in the order you named them; deleted_date_range_filter narrows it to a window.

Returns the v2 request to send, and the webhook payload QuickBooks' answer arrives in (this operation's response_json: its data shape and the status codes to handle).

Possible errors (error.code / error.type; the call result explains each): 1030 unsupported_request, 3150 missing_element, 3210 invalid_value, 3220 not_authorized, 3231 request_not_processed, 3250 feature_not_enabled, 3260 insufficient_permission, 3261 personal_data_access_denied, 3262 payroll_subscription_required, 3264 merchant_services_subscription_required

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "txn_del_type": "<txn_del_type>"
    },
    "name": "find_txn_deleteds"
  }
}

Input Schema

NameRequiredDescriptionDefault
meta_dataNoUse the `meta_data` attribute to control whether query responses include counts. Options are NoMetaData (default), MetaDataOnly (count only), and MetaDataAndResponseData (count plus objects).
request_idNoYour own label for the request, sent to QuickBooks as its qbXML `requestID` and echoed in the raw answer (`response_xml`); optional, since the answer's webhook already carries the request's `id`.
txn_del_typeYesThe type of transaction to be deleted.
include_qbxmlNoAlso return the qbXML this compiles to, for debugging. Not part of the v2 request.
include_ret_elementNo
deleted_date_range_filterNoFilters according to delete dates (within the last 90 days).

Output Schema

NameRequiredDescriptionDefault
urlYesReplace {connection_id} with the customer's connection.
qbxmlNoThe qbXML it compiles to. Only with include_qbxml.
queryYesThe query parameters: the arguments you passed.
methodYes
headersYesSend with the request. Resent unchanged when no 201 came back, it answers with the request already queued.
webhookYesJSON Schema of the payload POSTed to webhook_url once QuickBooks answers, with this operation's response_json (data shape and status codes).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing a non-obvious filtering pitfall (types not named are silently excluded, with an environment-specific observation), the 90-day retention bound, the grouping/ordering of results, and — critically — that the call returns a v2 request plus the webhook payload shape of QuickBooks' eventual answer rather than the data itself. The enumerated error codes add further behavioral context for failure handling.

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?

Front-loaded with the core behavior and the type-filter caveat, then return shape, then errors — a sensible order. The prose is dense and some sentences are long, but no sentence is redundant given the non-obvious pitfalls it covers.

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?

For a tool with a nested filter object, six parameters, and an output schema, the description covers scope, filtering semantics, returned fields and grouping, the async request/webhook return model, and the error surface. An agent has everything needed to call it 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 already 83%, so the baseline is 3; the description adds real meaning on top by explaining the strict semantics of `txn_del_type` (only named types are returned), the grouping order following the given type order, and what `deleted_date_range_filter` does to the result set. It also enumerates the returned fields tied to `include_ret_element`.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource with scope: 'Lists the transactions deleted in the last 90 days,' and constrains it by `txn_del_type`. It does not, however, name the sibling it most needs to be distinguished from (`find_list_deleteds`), so an agent must infer the distinction between list-entity deletions and transaction deletions.

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?

Provides actionable usage guidance: name every transaction type the app keeps, and be aware results are capped to a 90-day window with `deleted_date_range_filter` for narrowing. It stops short of naming alternatives or explicit when-not-to-use conditions.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources