Skip to main content
Glama

Business Calculator: GST, Margin & Everyday Formulas

Number Format, Units, Dates & Statistics Calculators — Saifs AI

numbers_dates_stats_calculators
Read-only

Format numbers and calculate dates, units and statistics exactly: round half-up / banker's / nearest ₹1 / 50 paise, Indian lakh-crore format 1,23,45,678.50, amount in words, lakh / crore ↔ million / billion, read '₹1.2 lakh'; convert kg / t / lb, cm / in, sq ft / acre, litre / CBM, dozen / gross, °C / °F; days between dates, working days with holidays, due dates, ageing days, month-end, Indian financial year and quarter; mean, weighted average, median, mode, std dev, percentile, quartiles, z-score; survey sample size, margin of error, confidence intervals; moving average, linear trend, correlation. Returns a standard-library Python script with only these calculators (number_format_calculator, unit_converter, date_due_date_calculator, average_statistics_calculator, survey_sample_calculator, trend_basic_calculator) to run in your code sandbox; each answer gives result, formula, inputs used, rounding, rule version and effective date. Inputs: tools (narrow to some of these calculators), calls ([{tool, operation, inputs, rounding?, as_of?}] baked into the script; a calculator from another area named in calls is added), calls_path (JSON file of calls in your sandbox). Calculation never runs on this server or any API. Not for EMI / interest / NPV / IRR (refused), nor forecasting with seasonality (MCP 18). Operation and input names: business_calculator_list_formulas.

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": "numbers_dates_stats_calculators"
  }
}

Input Schema

NameRequiredDescriptionDefault
callsNoCalculations to bake into the script (their calculators are included).
toolsNoNarrow the script to some of this area's calculators (default: all of them).
calls_pathNoJSON file of calls already in your sandbox.
full_catalogNoKeep descriptions and worked examples inside the script (larger).

Output Schema

NameRequiredDescriptionDefault
areaNo
notesNo
scriptYes
languageNo
requiresNo
calls_pathNo
operationsNo
call_formatNo
instructionsYes
writes_filesNo
calls_baked_inNo
engine_versionYes
included_toolsYes
server_computesNo
network_access_requiredNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Beyond the readOnly/openWorld annotations it discloses the crucial behavior that "Calculation never runs on this server or any API" and that the tool returns a standard-library Python script to execute in the sandbox. It also states each answer carries result, formula, inputs used, rounding, rule version and effective date. Minor gap: it doesn't mention the 500-call cap or what happens when calls and calls_path conflict.

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 capability, then inputs, then exclusions — a sensible order. However, the long semicolon-chained enumeration of every supported unit and statistic is heavy, and some of that detail is discoverable via business_calculator_list_formulas, making the single paragraph harder to scan than it needs to be.

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?

An output schema exists, so return values needn't be explained, and the description still covers the generation model, sandbox execution, per-answer metadata, parameter roles and refusal boundaries. For a code-generating multi-calculator tool, nothing an agent needs to invoke it correctly is missing.

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 baseline is 3; the description still adds meaning, notably that `tools` narrows the script, that `calls` are "baked into the script," that `calls_path` points at a file already in the sandbox, and that a calculator from another area named in `calls` is auto-added. It doesn't add much on rounding or as_of semantics beyond what the schema already says.

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 opening clause names specific verbs and resources ("Format numbers and calculate dates, units and statistics") and then enumerates the six concrete calculators it emits. It also draws a boundary against finance and forecasting siblings ("Not for EMI / interest / NPV / IRR (refused)"), so an agent can separate it from finance_mis_calculators without opening a schema.

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?

Explicit when-to-use coverage: it names the operations in scope, states that operations and input names live in business_calculator_list_formulas, and states what is out of scope and refused (EMI/interest/NPV/IRR) plus where seasonality forecasting belongs (MCP 18). Alternatives are named rather than inferred.

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.