Which response formats are supported?

Both OpenAI (choices[].message.tool_calls with function.arguments as a JSON string) and Anthropic (content[] blocks of type tool_use with an input object). The parser detects which one you pasted.

Why are OpenAI arguments a string?

OpenAI returns function arguments as a JSON-encoded string rather than a nested object. This parser decodes and re-formats them so you can read and validate the actual values.

What if my JSON is invalid?

The tool shows a clear parse error pointing at the problem rather than failing silently, so you can fix the paste and try again.

Is anything sent to a server?

No. All parsing happens in your browser. Nothing you paste is uploaded, stored, or logged.

Function Call Response Parser

Make sense of tool-call responses

When an LLM decides to call a tool, the response buries the useful part — which function, what arguments — inside a verbose JSON envelope, often with the arguments double-encoded as a string. Paste the raw response here and the parser extracts every call cleanly: function name, call ID, and pretty-printed arguments, for both OpenAI and Anthropic formats.

How it works

The parser first tries to read OpenAI’s shape (choices[].message.tool_calls[].function), where arguments is a JSON string it decodes and re-indents. If that’s absent it looks for Anthropic’s shape (content[] blocks of type tool_use with an input object). Either way you get a normalised list of calls. Invalid JSON produces a clear error instead of a blank screen.

Tips

If you’re debugging why your handler isn’t firing, check the arguments here first — malformed or missing fields are the usual culprit.
The pretty-printed arguments are valid JSON you can paste straight into a test for your function implementation.
For streaming responses, paste the fully-assembled final JSON, not individual chunks.