Skip to main content
Glama

QuBe Sync: QuickBooks Desktop API for developers

Create check

create_check
Read-onlyIdempotent

The amount of a check is the total of the amounts assigned to expense lines and item lines. You can write a check for:

The check_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": {
      "account_ref": "<account_ref>"
    },
    "name": "create_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
memoNoThe memo that is printed on the check itself.
addressNoIf an address request fails, some combination of address fields might be too long. In a Check, BillPaymentCheck, or SalesTaxPaymentCheck message, Address is the address that will print on the check.
txn_dateNoThe date written on the check. In some cases, if you leave `txn_date` out of an -Add message, QuickBooks will prefill `txn_date` with the date of the last-saved transaction of the same type.
def_macroNo`def_macro` lets you assign a reusable name to a returned `txn_id` or `txn_line_id` so later requests can reference it with `useMacro`. This feature requires SDK 2.0+.
ref_numberNo`ref_number` is a user-managed transaction reference (for example, a check number). It can be edited and is not guaranteed to be globally unique.
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`.
account_refYes`account_ref` points to an account in the company file. If both `full_name` and `list_id` are provided, `full_name` is ignored.
exchange_rateNo`exchange_rate` is the rate from this currency to the company’s home currency at AsOfDate. You can supply a rate when adding transactions, but QuickBooks does not provide rates through the SDK.
external_guidNoAllows for the attachment of a user defined GUID value.
include_qbxmlNoAlso return the qbXML this compiles to, for debugging. Not part of the v2 request.
item_line_addNoAn ItemLine is used to track any portion of a transaction that represents the purchase of an “item.” `item_line_add` and `item_group_line_add` combine: any number of each. QuickBooks receives them in that order: every `item_line_add`, then every `item_group_line_add`.
is_tax_includedNoFor future use with international versions of QuickBooks.
expense_line_addNo
is_to_be_printedNoIf `is_to_be_printed` is true, QuickBooks queues the form for later printing. It does not print immediately; printing is still a user action in QuickBooks.
payee_entity_refNo`payee_entity_ref` identifies the payee (customer, vendor, employee, or Other Name). If both `full_name` and `list_id` are provided, `full_name` is ignored.
sales_tax_code_refNo`sales_tax_code_ref` points to the sales-tax code used for an item or customer context. QuickBooks includes default TAX and NON codes, and a code can be deleted only when nothing references it.
include_ret_elementNo
item_group_line_addNoRefers to items that are grouped together in QuickBooks for fast entry. `item_line_add` and `item_group_line_add` combine: any number of each. QuickBooks receives them in that order: every `item_line_add`, then every `item_group_line_add`.
apply_check_to_txn_addNo

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

C2.4/5.0
Behavior3/5

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

The description goes beyond the annotations by disclosing the deferred-write model ("Returns the v2 request to send, and the webhook payload QuickBooks' answer arrives in") and by enumerating the full error taxonomy with codes, which is genuinely useful. That explanation also partly reconciles the readOnlyHint=true annotation with a tool named create_check, though the truncated "You can write a check for:" phrasing still reads as an immediate mutation. It does not say what happens on partial failure or whether a returned request must be sent before any check exists.

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 text is short but structurally broken: an explanatory fragment, a truncated bullet lead-in with no bullets, then an undifferentiated wall of ~20 error codes. Nothing is front-loaded with what the tool does, so the reader must reconstruct the purpose from the middle sentence. The error inventory is useful content delivered in the least scannable form.

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

Completeness2/5

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

For a 19-parameter, deeply nested tool with an output schema and read-only annotations, the description is under-built: it omits the required account, the expense-line vs item-line vs item-group-line vs apply-check-to-txn composition rules, and any sibling routing. The error list and the note about returning a v2 request plus webhook payload are the only substantial additions. Return values are covered by the output schema, so that gap is excused.

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 84%, so the schema already explains nearly all 19 parameters and the baseline is 3. The description adds one piece of meaning beyond the schema: that the check amount is the sum of expense-line and item-line amounts, which clarifies how the line arrays relate to the total. It says nothing about the required `account_ref` (the funding bank account) or about ordering/limits on the line arrays.

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

Purpose2/5

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

The description never states the operation cleanly: it opens with a fact about how a check's amount is computed and then cuts off at "You can write a check for:", leaving the actual list of supported scenarios missing. An agent must fall back on the name/title (create_check) and the incidental mention of the `check_add` qbXML wrapper to infer that this compiles a Check add request. It also never distinguishes this from create_bill_payment_check or create_sales_tax_payment_check.

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 beyond the implied "write a check", and no mention of when to prefer the sibling bill-payment or sales-tax-payment check tools, or update_check for existing checks. No prerequisites (bank account, payee, currency context) are stated. Usage is left entirely to inference from the tool name.

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