Skip to main content
Glama

QuBe Sync: QuickBooks Desktop API for developers

Find leads

find_leads
Read-onlyIdempotent

Builds a v2 lead.query request.

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

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_leads"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoThe string to match. Choose at most one of: `list_id`, or `name`, or the set (`from_modified_date`, `max_returned`, `name_filter`, `name_range_filter`, `to_modified_date`). Members of a set combine with each other, not with the other choices.
list_idNoQuickBooks' ID for the record. Used over `full_name` when both are sent. Choose at most one of: `list_id`, or `name`, or the set (`from_modified_date`, `max_returned`, `name_filter`, `name_range_filter`, `to_modified_date`). Members of a set combine with each other, not with the other choices.
iteratorNoPage through every match: QuBe Sync asks QuickBooks for each page in turn and sends each to your `webhook_url` as it arrives, all with the same `id`. On by default, with pages of 100 records; send `iterator=true` with `max_returned` for another size. Off when you send `iterator=false` (every match in one answer) or `max_returned` alone (at most that many, in one answer). It pages a filtered query only: with `list_id` or `name` every match comes back in one answer, so leave `iterator` out.
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`.
name_filterNoFilters according to the object’s Name. Choose at most one of: `list_id`, or `name`, or the set (`from_modified_date`, `max_returned`, `name_filter`, `name_range_filter`, `to_modified_date`). Members of a set combine with each other, not with the other choices.
max_returnedNoLimits the number of objects that a query returns. (To get a count of how many objects could possibly be returned, use the `meta_data` query attribute.) The page size, with `iterator=true`. Sent without `iterator`, or with `iterator=false`, it's a cap instead: at most this many records come back, in one answer, and QuickBooks doesn't say whether more matched. Choose at most one of: `list_id`, or `name`, or the set (`from_modified_date`, `max_returned`, `name_filter`, `name_range_filter`, `to_modified_date`). Members of a set combine with each other, not with the other choices.
include_qbxmlNoAlso return the qbXML this compiles to, for debugging. Not part of the v2 request.
to_modified_dateNoFilters results to objects modified on or before this timestamp. QuickBooks Desktop accepts 1970-01-01 through 2038-01-19T03:14:07. If only a date is provided, time defaults to end-of-day (23:59:59). Choose at most one of: `list_id`, or `name`, or the set (`from_modified_date`, `max_returned`, `name_filter`, `name_range_filter`, `to_modified_date`). Members of a set combine with each other, not with the other choices.
name_range_filterNoFilters according to the object’s Name. Choose at most one of: `list_id`, or `name`, or the set (`from_modified_date`, `max_returned`, `name_filter`, `name_range_filter`, `to_modified_date`). Members of a set combine with each other, not with the other choices.
from_modified_dateNoFilters results to objects modified on or after this timestamp. QuickBooks Desktop accepts 1970-01-01 through 2038-01-19T03:14:07. If only a date is provided, time defaults to 00:00:00. Choose at most one of: `list_id`, or `name`, or the set (`from_modified_date`, `max_returned`, `name_filter`, `name_range_filter`, `to_modified_date`). Members of a set combine with each other, not with the other choices.
include_ret_elementNo

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

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description does add real value beyond that: it discloses the non-obvious architecture that the query is not executed inline but emitted as a v2 request whose answer arrives asynchronously via webhook, and it enumerates the concrete error codes to handle (e.g. 3260 insufficient_permission, 3220 not_authorized). It stops short of describing auth requirements, rate limits, or what an empty parameter set does.

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?

The structure is well front-loaded: purpose first, then return shape, then failure modes. The long error-code enumeration is dense but each entry pairs a code with a symbolic name, so it is skimmable rather than wasted. Minor trimming possible, no filler sentences.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter tool with nested objects and zero required parameters, the description leaves meaningful questions open: what happens when no parameters are sent, whether authorization to QuickBooks must already exist, and where the webhook_url/id referenced in the schema actually come from. An output schema exists, so return values need not be explained, yet the description still spends a clause on response_json shape. Adequate but not complete for this complexity.

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

Parameters3/5

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

Schema description coverage is 92%, so the schema itself carries nearly all parameter meaning, and the description adds nothing about individual parameters such as iterator, meta_data, or the mutually exclusive sets. Baseline 3 applies. Worse, the iterator schema text references a `webhook_url` and a shared `id` that do not appear among the 12 parameters, and the description does not resolve that inconsistency.

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?

The description names a specific verb and resource: it "Builds a v2 lead.query request" for QuickBooks leads, which is concrete enough to separate it from the sibling find_* tools that target other entities. It also states what comes back (the compiled request plus the webhook payload shape). The only friction is tension between the name/title 'find_leads' and the fact that the tool compiles a request rather than returning leads directly — an agent could momentarily misread it as an executing query.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use or when-not-to-use guidance, no mention of prerequisites such as QuickBooks connection or authorization, and no routing to alternative tools for related lookups. The only selectivity expressed (mutually exclusive parameter sets, iterator vs. max_returned behavior) lives entirely in the input schema, not the description.

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