Skip to main content
Glama

QuBe Sync: QuickBooks Desktop API for developers

Report confusion

report_confusion

Send feedback to the QuBe Sync team about something in this server, its guides, or the v2 API that confused you, so we can fix it. Use it when a tool description or guide was unclear or contradicted what actually happened, an error didn't say how to fix it, you had to guess a parameter, endpoint, or behavior, or you couldn't find a way to do what your user needed. Make one call per problem, after you've got past it or given up, and put what the answer turned out to be in answer. Not for praise, and not for bugs in your user's own app. The QuBe Sync team stores and reads these reports: never include API keys, webhook secrets, your user's code, or QuickBooks data such as customer names and amounts -- describe the problem in terms of our tools and docs.

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": {
      "summary": "<summary>",
      "kind": "<kind>",
      "details": "<details>",
      "outcome": "<outcome>"
    },
    "name": "report_confusion"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYesunclear: a description or guide left you unsure what to do. wrong: it contradicted what actually happened. unhelpful_error: an error didn't say how to fix it. missing: you couldn't find a way to do what you needed.
agentNoYour client and model, e.g. "Claude Code / claude-opus-5-5".
answerNoWhat actually worked, or what the docs should have said. The most useful part of a report.
detailsYesWhat you were trying to do, what you expected, and what happened instead.
outcomeYesresolved: you found the right answer. worked_around: you did something else instead. blocked: you couldn't continue.
subjectNoThe tool, endpoint, or guide involved, e.g. "create_invoice", "POST /api/v2/workflow-templates/{key}/install", "get_workflow_authoring_guide".
summaryYesOne line naming the problem and where it is, e.g. "create_invoice: unclear whether a line's item takes a name or a ListID".

Output Schema

NameRequiredDescriptionDefault
idYesThe stored report's id.
storedYesfalse when this address has already sent its limit of reports this hour; don't retry.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare this is a non-read-only, non-destructive, non-open-world write; the description goes well beyond them by disclosing that the QuBe Sync team stores and reads every report, which is the fact that drives the scrubbing rules. It then names the concrete sensitive classes that must never appear (API keys, webhook secrets, user code, QuickBooks customer names and amounts). Nothing here contradicts the annotations.

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 core purpose and trigger list are front-loaded, and the privacy constraint is placed last where it reads as a final guardrail rather than a preamble. The middle sentences are dense but each covers distinct ground; the only slight redundancy is between the trigger list and the `kind` enum descriptions in the schema.

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?

With an output schema present, return values need no explanation, and the description fills the remaining gaps: who consumes the report, when to file one, how often, and what must be redacted. For a 7-parameter feedback tool, an agent has everything needed to file a well-formed, safe report on the first attempt.

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 100%, so the schema already carries the per-field meaning and enum definitions, making 3 the baseline. The description earns one step above it by telling the agent how to fill `answer` (what the answer turned out to be, framed as the most valuable content) and by tying report granularity to `summary` via one call per problem. It does not add syntax or length guidance beyond the schema.

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

Purpose5/5

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

The first sentence states a concrete verb and resource (send feedback to the QuBe Sync team) and scopes the subject matter to this server, its guides, and the v2 API. It is unmistakably not one of the create_* QuickBooks entity siblings, so an agent can route to it on the name alone.

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

Usage Guidelines5/5

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

It enumerates the trigger conditions explicitly (unclear or contradicted descriptions, unhelpful errors, guessed parameters, dead ends) and closes the loop with exclusions: not for praise, not for bugs in the user's own app. It also gives timing guidance (one call per problem, after you've got past it or given up), which is exactly the kind of when-to-use detail most definitions omit.

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