Which formats are supported?

OpenAI's messages array with assistant tool_calls and role:'tool' results, and Anthropic's messages with tool_use and tool_result content blocks. You can paste the request messages, the response, or both combined.

My JSON didn't parse — what happened?

The input must be valid JSON — either an array of messages or an object containing a messages/content array. Copy the exact array from your API logs; a trailing comma or wrapping prose will break parsing.

Is my trace uploaded?

No. Parsing and rendering happen entirely in your browser. Nothing you paste is sent to a server, stored or logged.

Can it handle parallel tool calls?

Yes — when an assistant turn contains multiple tool calls they are shown as sibling steps, and each matching tool result is linked by its call ID where available.

Tool Use Trace Visualizer

See an LLM tool-use trace as a readable flow

Debugging an agent means reading deeply nested JSON: assistant messages, tool_calls with stringified arguments, and tool results scattered across the array. This tool parses an OpenAI or Anthropic tool-use conversation and lays it out as a numbered, color-coded flow — model message → tool call → tool result → next model message — so you can follow the loop at a glance. It runs entirely in your browser.

How it works

The parser walks the messages/content array and classifies each element:

Model text — assistant content strings (or Anthropic text blocks).
Tool call — OpenAI tool_calls[].function (name + JSON arguments) or Anthropic tool_use blocks. Arguments are pretty-printed.
Tool result — OpenAI role: "tool" messages or Anthropic tool_result blocks, linked back to their call by tool_call_id / tool_use_id when present.

Each step is rendered as a card with a type badge, so the model↔tool handshake is obvious and you can immediately see a malformed argument or an unexpected result.

Tips and notes

Paste the full messages array for the richest view — request-only shows the calls, response-only shows the results, and both together show the loop.
If arguments are a JSON string (OpenAI style), they are parsed and pretty-printed; invalid JSON arguments are shown raw so you can spot the bug.
Parallel tool calls in a single turn appear as sibling steps — handy for confirming the model fanned out the way you expected.