Skip to main content
Glama

QuBe Sync: QuickBooks Desktop API for developers

Create to do

create_to_do
Read-onlyIdempotent

A “to do”list is used in QuickBooks to keep track of tasks. Notice the Notes field: when you do a query on the ToDo list (ToDoQuery), you can use the supplied name filters to search these Notes and filter by them.

The to_do_add wrapper from qbXML is also accepted. 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, 3000 invalid_object_id, 3040 invalid_amount, 3070 string_too_long, 3120 object_not_found, 3140 invalid_reference, 3150 missing_element, 3175 in_use, 3176 locked, 3180 cannot_save, 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, 3263 read_only_access, 3264 merchant_services_subscription_required, 3270 missing_posting_account

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": {
      "notes": "<notes>"
    },
    "name": "create_to_do"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoType may have one of the following values: Task [DEFAULT], Call, Fax, Email, Meeting, Appointment
notesYesAdditional information.
is_doneNoIf `is_done` is true, this “to do” task has been completed. The default value of `is_done` is false.
lead_refNoThe lead list contains information about leads for a company. Choose at most one of: `customer_ref`, or `employee_ref`, or `lead_ref`, or `vendor_ref`.
priorityNoPriority may have one of the following values: Low [DEFAULT], Medium, High
is_activeNoIf `is_active` is true, this object is currently enabled for use by QuickBooks. The default value is true.
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`.
vendor_refNoA vendor is any person or company from whom a small business owner buys goods and services. (Banks and tax agencies usually are included on the vendor list.) Choose at most one of: `customer_ref`, or `employee_ref`, or `lead_ref`, or `vendor_ref`.
customer_refNo`customer_ref` identifies a customer or customer job. If both `full_name` and `list_id` are provided, `full_name` is ignored. In SalesReceipt and ReceivePayment, it identifies who receives credit. Choose at most one of: `customer_ref`, or `employee_ref`, or `lead_ref`, or `vendor_ref`.
employee_refNoThe employee list contains payroll information about each of the company’s employees. Choose at most one of: `customer_ref`, or `employee_ref`, or `lead_ref`, or `vendor_ref`.
include_qbxmlNoAlso return the qbXML this compiles to, for debugging. Not part of the v2 request.
reminder_dateNoThe date on which the contents of the Notes string will appear on the Reminder list within QuickBooks.
reminder_timeNoThe time on which the contents of the Notes string will appear on the Reminder list within QuickBooks.
include_ret_elementNo

Output Schema

NameRequiredDescriptionDefault
urlYesReplace {connection_id} with the customer's connection.
bodyYesThe JSON body: the arguments you passed.
qbxmlNoThe qbXML it compiles to. Only with include_qbxml.
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

C2.7/5.0
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 by explaining the compilation model ("Returns the v2 request to send, and the webhook payload QuickBooks' answer arrives in") and by enumerating error codes/types with their meanings, which is behavior beyond the annotations. But it never explains why a 'create' tool is read-only, nor whether the record is actually persisted or merely queued as a request.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The lead sentence is a domain definition rather than the action, so the payload is mis-front-loaded. The 25-entry error-code dump consumes most of the text and would be better as structured data, while the crucial fact about what the tool actually produces is buried in a parenthetical.

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?

With 14 parameters, a 93%-covered schema, and an output schema, the structural burden is largely carried elsewhere, and the error catalogue covers failure handling well. What is missing is the operation's essential framing: that this compiles a request rather than performing a write, and which of the mutually exclusive party refs matters for a to-do.

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 93% with an output schema present, so the baseline is 3. The description's only parameter-level contribution is the note that Notes content is searchable via ToDoQuery name filters, which is marginal meaning-add over the schema's own per-field docs.

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

Purpose3/5

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

The description opens with a domain fact ("A 'to do' list is used in QuickBooks to keep track of tasks") rather than a verb+resource statement of what the tool does, and the only concrete action cue is the incidental mention of the "`to_do_add` wrapper from qbXML". An agent can infer creation from the name and that wrapper reference, but the description itself never plainly says "adds a to-do item" nor distinguishes this from update_to_do.

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 guidance and no mention of alternatives (e.g. update_to_do for existing items or find_to_dos for retrieval). The only cross-reference is to ToDoQuery, which is a different product surface and is framed as a note about the Notes field rather than as guidance for choosing this tool.

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