What schema formats are supported?

It accepts the OpenAI function shape (with a function.parameters object), the Anthropic tool shape (with an input_schema object), or a bare JSON Schema object. It reads the parameters block from whichever it finds.

How are values chosen?

Strings derive from the field name (an "email" field becomes user@example.com), numbers take the midpoint of any minimum and maximum, enums pick the first option, arrays produce two sample items, and nested objects are generated recursively. Output is deterministic — the same schema always produces the same mock. The aim is type-correct, plausible data, not real data.

Why mock instead of calling the API?

When you are building the code that parses and handles tool calls, you need many varied, deterministic inputs. Mocking gives you free, instant, repeatable fixtures without burning tokens or hitting rate limits.

Does anything get uploaded?

No. The schema is parsed and the mock is generated entirely in your browser.

Function Call Mock Response Generator

Function call mock generator

Building the code that handles an LLM’s tool calls means you need example tool-call payloads to test against — but calling the real API for each one is slow and costs tokens. This tool reads your function/tool JSON Schema and synthesises type-correct mock arguments, giving you instant fixtures for your parsing and handler logic.

How it works

The input is parsed as JSON and the tool locates the parameters schema — under function.parameters (OpenAI), input_schema (Anthropic), or at the top level (bare JSON Schema). It then walks the schema recursively: enum fields take their first option, strings derive a plausible value from the property name, numbers take the midpoint of minimum/maximum, booleans default true, arrays produce two sample items, and nested objects recurse. Generation is deterministic, so the same schema always yields the same mock. The result is wrapped in a realistic tool-call envelope you can paste straight into a test.

Tips and notes

Every property is included. The generator emits all defined properties, not just the required ones, so the mock exercises your full parsing path.
Use enums for realism. Enum constraints produce the most believable mock values since the generator picks a real allowed option.
Add minimum/maximum to shape numbers. Numeric fields default to the midpoint of the declared range, so set bounds to get the value you want to test.
It validates structure, not semantics. The mock satisfies the schema’s types; it will not invent business-meaningful data, so adjust values by hand where your tests assert on specifics.