What does strict mode change?

Strict function calling requires every property to be listed in required and additionalProperties to be false, which makes the model's arguments schema-guaranteed.

How do the platform formats differ?

OpenAI nests the schema under function.parameters, Anthropic uses input_schema, Gemini uses functionDeclarations[].parameters and MCP uses inputSchema — same JSON Schema, different wrapper.

Why does parameter description matter so much?

The model picks tools and fills arguments purely from names and descriptions, so a clear one-line description per parameter is the single biggest reliability win.

Can I get TypeScript instead of JSON?

Yes — choose the Vercel AI SDK target to export a typed tool() definition with a matching Zod input schema.

Is my data uploaded to a server?

No. This tool runs entirely in your browser using standard web APIs, so your input never leaves your device and nothing is logged or stored on our servers.

AI Tool Schema Builder

Build function-calling schemas for OpenAI, Claude, Gemini, MCP and the AI SDK.

Support

Works Offline

Privacy First

No Login

No API

Tool definition

Target format

Strict mode

All properties required, no extras

Function name

DescriptionThe model chooses tools from this text

Parameter name

Type

Description

Allowed values (comma separated)

Required

Parameter name

Type

Description

Allowed values (comma separated)

Required

Generated schema

JSON

{
  "type": "function",
  "function": {
    "name": "get_weather",
    "description": "Get the current weather for a city.",
    "parameters": {
      "type": "object",
      "properties": {
        "city": {
          "type": "string",
          "description": "City name, e.g. Tokyo"
        },
        "unit": {
          "type": "string",
          "description": "Temperature unit",
          "enum": [
            "celsius",
            "fahrenheit"
          ]
        }
      },
      "required": [
        "city",
        "unit"
      ],
      "additionalProperties": false
    },
    "strict": true
  }
}

About the AI Tool Schema Builder

Describe a tool and its parameters in a form, then export the exact shape each platform expects: OpenAI function calling with strict mode, Anthropic input_schema, Gemini function declarations, MCP inputSchema, or a ready-to-paste Vercel AI SDK tool with a Zod schema.

Examples

Weather tool

YAMLname: get_weather, params: city, unit

Output

JavaScript{ "type": "function", "function": { … } }

Keyboard shortcuts

Copy the main outputCtrl / ⌘ + Shift + C
Download the resultCtrl / ⌘ + S
Share this toolCtrl / ⌘ + Shift + S
Reset the inputsAlt + R
Open the tool search paletteCtrl / ⌘ + K

Related tools

AI Tool Schema Converter

AI & LLM

Convert function-calling schemas between OpenAI, Anthropic, Gemini and MCP.

JSON Schema to AI Tool Schema

AI & LLM

Wrap any JSON Schema into a ready-to-use function-calling tool.

LLM Structured Output Validator

AI & LLM

Check that a model's JSON reply matches your JSON Schema.

MCP Tool Schema Validator

AI & LLM

Validate Model Context Protocol tool definitions before you ship them.

MCP Tool Schema Generator

AI & LLM

Generate an MCP, OpenAI or Anthropic tool schema from example arguments.

AI Dataset Deduplicator

AI & LLM

Remove exact and near-duplicate rows from fine-tuning datasets.

Frequently asked questions

Version 1.0.0 · Updated 2026-08-14 · Runs entirely in your browser