Skip to main content
Glama

Avanciq - tax rates, codes, e-invoices, calculation checks

Check business arithmetic to the cent

verify_calculation
Read-onlyIdempotent

1 call. Recomputes a business calculation exactly (decimal, stated rounding) and says whether a claimed result is correct: invoice/claim totals with discounts and shipping, GST/VAT invoices, loan interest and amortisation, depreciation, FX with markup and fees, FIFO / moving-average inventory, weekly payroll overtime, trade quotes. Use it before giving the user any total you computed yourself, or to check a number another AI produced. Input fields per kind: call coverage (free).

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": {
      "kind": "<kind>",
      "inputs": "<inputs>"
    },
    "name": "verify_calculation"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYesWhich calculation.
inputsYesThe numbers, e.g. loan_interest {principal, annual_rate_percent, days, day_count 365|360}; invoice_or_claim_total {lines[{quantity, unit_price, discount_percent?}], invoice_discount_percent?, shipping?, tax_rate_percent?, tax_on_shipping?, amount_paid?}. Full field list per kind: coverage.
claimed_resultNoOptional: the number (or object of named numbers) to check, e.g. 49.32 or {"interest": 49.32}.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, closed-world, non-destructive behavior, so the description is not burdened with safety disclosure. It adds real context beyond them: exact decimal arithmetic with stated rounding, a correctness verdict against a claimed result, and a '1 call' cost signal. It stops short of describing what the response contains when a claim is wrong (e.g., expected vs. claimed).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the operative fact ('1 call'), then the purpose, then the usage rule, then the kind list, then the field-coverage pointer. Every sentence carries distinct information; the kind enumeration is long but directly maps to the enum and helps an agent self-select.

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

Completeness4/5

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

No output schema exists, and the description does cover the return in substance — it computes exactly and reports whether the claimed result is correct. For a read-only deterministic calculator that is nearly sufficient, though the shape of a negative verdict and any rounding-tie behavior are left implicit.

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%, and the schema itself carries the enum and nested-field examples, so the baseline would be 3. The description adds value by grouping the nine kinds into business scenarios and by explicitly routing to the coverage tool for the full per-kind field list, which prevents guesswork on nested inputs.

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: 'Recomputes a business calculation exactly (decimal, stated rounding) and says whether a claimed result is correct.' It is clearly distinguishable from siblings like vat_rate or einvoice_check, and the enumerated kinds clarify the problem domain without opening the schema.

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

Usage Guidelines4/5

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

Explicitly instructs when to call: 'before giving the user any total you computed yourself, or to check a number another AI produced.' No when-not conditions or error-case exclusions are given, but the 'free' routing to the coverage sibling for per-kind field lists provides a concrete alternative path for agents that only need schema detail.

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