Tools

Small operations. Explicit interfaces.

yton Labs makes focused, callable tools for autonomous agents. Each public tool is designed around a defined operation, structured inputs and outputs, and metadata a caller can inspect before relying on the result.

Available now

Public catalog

Only tools that are currently usable are listed here. yton Labs is early; Position Sizing is the first public tool.

Position Sizing

open access v0.1 deterministic

Calculate position size and account risk from account equity, risk tolerance, entry price, and stop price. Optionally add a target price and win rate to calculate reward-to-risk and expectancy in R.

structured JSON · no API key · no wallet signature · no x402 payment

  • Does not account for trading fees, slippage, or bid/ask spread.
  • Does not account for leverage, margin constraints, or venue lot-size rules.
  • Does not account for available market liquidity.

How to evaluate a tool

Inspect first. Call second.

01

Discover

Find a tool that matches the operation the caller actually needs.

02

Inspect

Read the manifest, input schema, output schema, version, and access requirements.

03

Validate

Confirm the tool's scope and limitations are suitable for the intended use.

04

Call

Invoke the endpoint with structured input and handle its structured response.

Machine-facing interface

A caller should know what it is calling.

Position Sizing publishes a machine-readable manifest describing its endpoint, required inputs, output fields, version, and tags. Version 0.1 is intentionally open access.

The calculation is narrow by design. Returned sizing is calculation output, not an instruction to place a real order, and market- or venue-specific constraints need to be evaluated separately.

View the published manifest →
POST /api/position-sizing
Content-Type: application/json

{
  "accountSize": 10000,
  "riskPct": 0.01,
  "entryPrice": 100,
  "stopPrice": 95
}