Skip to main content
Glama

TrueCalci

by com.truecalci
OverviewDiscussionsAdmin

FX invoicing and conversion

fx_invoicing
Read-onlyIdempotent

Quantify cross-border payment fee drag and calculate net landed local currency across 6 global payout rails (Wise, Deel, Stripe, Payoneer, PayPal, and SWIFT wire) against mid-market FX benchmark rates.

Behavior: Deterministic, idempotent calculation with zero external side effects. Models fixed per-transaction wire fees, percentage platform fees, and hidden foreign exchange percentage spreads for each provider. Returns ranked table with landed payout amounts, total drag percentage, hidden FX markup, and savings versus worst-case rail.

Usage Guidelines: Use when an international freelancer, remote worker, or cross-border vendor needs to determine the cheapest payout rail or invoice amount in USD. Do not use for domestic US employee vs contractor parity; use contractor_parity instead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
as_of_dateYesCivil date YYYY-MM-DD. Selects the rule pack in force on that date. Required: the engine will not assume a date.
invoiceUsdYesGross billed invoice amount in USD ($). Must be a positive number greater than 0.
targetCurrencyNoPayout destination currency code: 'EUR' (Euro), 'GBP' (British Pound), 'CAD' (Canadian Dollar), 'AUD' (Australian Dollar), 'INR' (Indian Rupee), 'SGD' (Singapore Dollar), 'BRL' (Brazilian Real), 'MXN' (Mexican Peso), or 'PHP' (Philippine Peso).EUR

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / as_of_date
      Added value: +{
+  "description": "Civil date YYYY-MM-DD. Selects the rule pack in force on that date. Required: the engine will not assume a date.",
+  "example": "2026-09-26",
+  "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "invoiceUsd"
-]New value: +[
+  "invoiceUsd",
+  "as_of_date"
+]
  2. Changed1 schema field changed
    • removedInput schema / properties / invoiceUsd / default
      Removed value: -10000
  3. Changed2 schema fields changed
    • changedInput schema / properties / invoiceUsd / description
      Previous value: -"Gross invoice amount in USD ($)"New value: +"Gross billed invoice amount in USD ($). Must be a positive number greater than 0."
    • changedInput schema / properties / targetCurrency / description
      Previous value: -"Target local payout currency code"New value: +"Payout destination currency code: 'EUR' (Euro), 'GBP' (British Pound), 'CAD' (Canadian Dollar), 'AUD' (Australian Dollar), 'INR' (Indian Rupee), 'SGD' (Singapore Dollar), 'BRL' (Brazilian Real), 'MXN' (Mexican Peso), or 'PHP' (Philippine Peso)."
  4. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description correctly reinforces these with 'Deterministic, idempotent calculation with zero external side effects.' It adds useful behavioral context beyond annotations: what fee components are modeled and what the returned ranked table contains. No contradiction exists.

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?

The description is appropriately structured into purpose, behavior, and usage guidelines. Every sentence earns its place: the first gives the high-level result, the second defines deterministic behavior and output, and the third routes the agent to or away from the tool. No filler or redundancy.

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?

For a read-only, idempotent calculator with a fully described 3-parameter schema, the description is complete. It explains what is modeled, which providers are included, what the returned ranked table contains, and when to prefer an alternative. Even without an output schema, an agent has enough to select and invoke the tool correctly.

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%: invoiceUsd, as_of_date, and targetCurrency already have clear descriptions, defaults, and an enum. The tool description does not need to repeat parameter-level details, so baseline 3 applies; it adds no specific parameter meaning beyond the schema, but nothing is missing.

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 description opens with a specific verb-resource pair: 'Quantify cross-border payment fee drag and calculate net landed local currency across 6 global payout rails.' It names the rails explicitly and contrasts with contractor_parity, so an agent can distinguish this tool from its siblings without inspecting schemas.

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?

The 'Usage Guidelines' section states exactly when to use the tool (international freelancers, remote workers, cross-border vendors choosing a payout rail or invoicing in USD) and explicitly says when not to use it (domestic US employee vs contractor parity), naming the alternative tool. This is model guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All TrueCalci toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources