Skip to main content
Glama

BillTally

Audit Bill, Match Bank CSV & Export Verified Pack (1-Call)

audit_and_export_pack
Read-onlyIdempotent

All-in-one compound audit tool: penny-verifies a supplier bill, optionally matches it against pasted bank statement CSV text or transactions, mints a 14-day shareable Verified Dispute Link (/v/) with SHA-256 checksum, and generates a downloadable 3-tab Excel (.xlsx) workbook with live =SUM() formulas or QuickBooks CSV in a single round-trip.

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": {
      "raw_text": "<raw_text>"
    },
    "name": "audit_and_export_pack"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNoSpreadsheet output format (xlsx, csv, or quickbooks_csv).xlsx
api_keyNoOptional BillTally Pro API key.
raw_textYesRaw supplier bill, receipt, or CAM reconciliation text to verify.
bundle_nameNoOptional label for the exported spreadsheet filename.
workspace_idNoOptional workspace identifier for quota tracking.
bank_csv_textNoOptional pasted bank statement CSV or line text to cross-match against the bill.
bank_transactionsNoOptional structured bank withdrawal rows to cross-match against the bill.
use_corrected_amountsNoWhen true, exports verified true math totals instead of overcharged billed totals.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior3/5

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

The description adds real behavioral context beyond the annotations: the dispute link expires in 14 days, carries a SHA-256 checksum, and the workbook contains live =SUM() formulas across 3 tabs. However, it also says the tool "mints" a persistent shareable resource, which sits in tension with readOnlyHint=true; that side effect is not reconciled anywhere. Permission, quota (workspace_id is only labeled "for quota tracking"), and failure behavior are left unstated.

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?

It is a single dense sentence, but the compound nature is front-loaded and each clause maps to a distinct output artifact, so little is wasted. Slightly long for one sentence and would scan better split by stage (verify, match, link, export).

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 an 8-parameter compound tool with no output schema, the description covers the main artifacts (link, xlsx, CSV) but not response structure, what happens when bank matching finds no match, error conditions, or how the dispute link is authorized. Adequate to attempt a call, incomplete for predicting results.

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 already 100%, so the baseline is 3, but the description earns a bump by explaining what the format values produce (3-tab xlsx with live formulas vs QuickBooks CSV), what bank_csv_text and bank_transactions are for (optional cross-matching), and what use_corrected_amounts changes (verified true totals vs overcharged billed totals). It does not clarify api_key tiers, bundle_name effects, or what workspace_id quota means in practice.

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 description names concrete verbs and artifacts: penny-verifies a supplier bill, matches an optional bank CSV, mints a /v/<id> dispute link, and exports a 3-tab xlsx or QuickBooks CSV. That is far more specific than the title alone and lets an agent tell this compound tool apart from a simple exporter. It stops short of 5 because it never names the sibling tools (export_ledger_bundle, reconcile_invoices_with_bank_ledger, extract_financial_documents) or states how this bundled flow differs from chaining them.

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?

Usage is implied by "All-in-one compound audit tool" and "in a single round-trip," which suggests choosing this over multiple separate calls when a bill-to-bank audit plus export is wanted. "Optionally" correctly marks bank matching as conditional. There is no explicit when-not guidance, no prerequisites such as whether an API key is required for the dispute link, and no statement about when to prefer the sibling reconcile or export tools.

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