Skip to main content
Glama

HelloBooks AI Agents MCP Server

analyze_qbo_journal_anomalies

Read-only

Scan a QuickBooks Online "Journal Entries" CSV export for anomalies — currently round-number lines (debit or credit amounts that are exact multiples of $1,000, above a $1,000 materiality threshold). Round numbers are statistically rare in real bookkeeping and frequently indicate estimates, plugs, or fraud signals worth review. Input is raw CSV text from QBO Reports → Accountant → Journal. Max 5,000 rows; max 5 MB. Returns flagged lines with severity ($100K+ high, $10K+ medium, else low) and a shareable URL. Use this when a user pastes QBO data and asks "any anomalies?", "look for round numbers", or "anything suspicious". Tier-0 subset — HelloBooks Phase 3.0 anomaly detection in the paid product additionally catches GL outliers vs entity history, vendor-history mismatches, archived-vendor activity, and AI-narrated suspicious lines (which require the live HelloBooks 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": {
      "csvText": "<csvText>"
    },
    "name": "analyze_qbo_journal_anomalies"
  }
}

Input Schema

NameRequiredDescriptionDefault
csvTextYesRaw CSV text of a QuickBooks Online "Journal Entries" report. Export from QBO: Reports → Accountant → Journal → Export as CSV. Paste the file contents directly.
fileNameNoOptional original filename, used only as a label on the share page.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already mark it read-only and closed-world, and the description still adds real operational detail: input size ceilings (5,000 rows / 5 MB), the severity bucketing rules ($100K+ high, $10K+ medium, else low), and the fact that a shareable URL is produced. Nothing an agent would need to predict behavior is left implicit.

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?

Front-loaded with the verb, resource, and detection rule, then limits, then return shape, then usage. The closing Tier-0/paid-product sentence is longer than strictly necessary and reads partly as product positioning, though it does convey scope boundaries.

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?

There is no output schema, so the description compensates by describing the return payload (flagged lines, severity tiers, shareable URL). For a two-parameter, annotation-covered tool, an agent has everything needed to call and interpret it.

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 100% and the schema already documents the export path, length bounds, and the fileName-as-label role, so the description's restatement adds little beyond confirming raw CSV text is the input. Baseline 3 applies since the schema carries parameter meaning.

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?

States a specific verb and resource ("Scan a QuickBooks Online Journal Entries CSV export for anomalies") and narrows the current detection scope to round-number lines above a materiality threshold. Naming QBO and the CSV input distinguishes it from the Xero and cleanup siblings without needing to enumerate them.

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?

Gives concrete trigger phrases ("any anomalies?", "look for round numbers", "anything suspicious") tied to a user pasting QBO data, and explicitly bounds the scope by listing what this Tier-0 tool does not catch (GL outliers, vendor-history mismatches, archived-vendor activity, AI narration) — that is a genuine when-not statement.

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.