Skip to main content
Glama

QuBe Sync: QuickBooks Desktop API for developers

List workflow templates

list_workflow_templates
Read-onlyIdempotent

Lists the workflow chart templates QuBeSync ships (key, name, description): complete, tested charts for the common multi-step jobs. These match names -- ranked against the connection's name index (ACME, Inc. finds Acme Inc) -- and ask your app about near matches: resolve (any list record by kind and name -- a customer, a job, a vendor, an item, an account -- or the ListID it stored), ensure (resolve, then create what is missing, asking when the name is held elsewhere in its name space), upsert (resolve, then update, or create, asking as ensure does when the name is held elsewhere), push_records (many upserts) and add_transaction (any transaction add, once every customer, item, class or account it names exists: it finds each and asks every question first, then creates what is missing by a rule per kind). The rest: resolve_transaction (a transaction by id, number or GUID); record a payment (asking when it's more than the invoice owes, or the invoice isn't there); void a transaction; read the company's profile (company, preferences, host); pull every record, or those changed and deleted since a date, paged to your app (pull_changes, stream_query). A workflow runs server-side against a connection, settles requests QuickBooks never answered, asks before overwriting a record someone else changed, and can pause for a decision from your app. Workflows run on realtime and simulated connections only (a standard one answers 422 realtime_required). Install one as-is, child workflows included, with POST /api/v2/workflow-templates/{key}/install (body {"publish": true}; add "replace": true to re-install over workflows the app already has); fetch it with get_workflow_template to read or adapt it first.

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": "list_workflow_templates"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds marginally relevant context in the connection constraint (workflows run on realtime and simulated connections only; standard returns 422 realtime_required) and the install/replace endpoint semantics, but says nothing about the listing itself such as ordering, completeness, or whether results are filtered. Adding the 422 constraint and install semantics is useful, but most of it applies to workflow execution, not to this call.

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 purpose is front-loaded correctly, but the remaining text is a sprawling tour of the entire workflow engine (resolve/ensure/upsert/push_records/add_transaction by kind, payment edge cases, voiding, profile reads, pull_changes) that does not help an agent call a zero-parameter list tool. Much of it reads as a system overview pasted into a listing tool's description.

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 no-param, read-only lister, the call itself needs little explanation and the definition supplies the follow-up path (get_workflow_template to read/adapt, install endpoint). But it omits anything about the returned collection's size or shape and spends its length on off-topic workflow semantics, so completeness is achieved incidentally rather than by design.

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?

The tool takes zero parameters, so the baseline is 4. The description does at least state the returned fields (key, name, description), which helps the agent understand what the empty schema implies, with no contradiction.

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 opening sentence gives a specific verb and resource: 'Lists the workflow chart templates QuBeSync ships (key, name, description)', with a concrete characterization of what those templates are. However, the bulk of the description then describes workflow request semantics (resolve, ensure, upsert, push_records, add_transaction) rather than the listing operation, which dilutes focus. The sibling get_workflow_template is named, so an agent can partially distinguish the two.

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

Usage Guidelines3/5

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

It gives one real routing hint: 'fetch it with get_workflow_template to read or adapt it first', which implies list-then-fetch. But it never says when to use this versus find_templates, and the tail of the description hands the agent an unrelated HTTP install procedure (POST /api/v2/workflow-templates/{key}/install) without clarifying that installing is not something this read-only tool does.

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