Free tool / build
Is your tool setup right?
Paste your agent's tool definitions. Find the mistakes that make agents pick the wrong tool or send bad arguments.
No sign-up / OpenAI, Anthropic, MCP, Gemini
Catch tool mistakes before the model does.
Paste the tools array you send to the model. You will get a score, a list of problems in plain words, and how many tokens the definitions cost on every call.
This checks structure and clarity, not whether your tool works. It follows the documented rules of each provider's tool format. A high score means fewer avoidable mistakes, not that the model will always choose well.
How it works
Three steps, no sign-up.
- 01
Paste your tools
The array you send to the model. OpenAI, Anthropic, MCP and Gemini formats are recognised.
- 02
Read the problems
Names, descriptions, missing types, required fields, loose schemas and provider-specific rejections, in plain words.
- 03
Fix and re-check
Each problem has a fix. Paste again to see the score go up.
Questions people ask
Which formats are supported?
OpenAI Chat Completions and Responses, Anthropic, MCP (the tools/list response) and Gemini function declarations. You can paste a single tool, a list or an object with a tools list.
Why do descriptions matter so much?
Models choose tools by reading names and descriptions. A vague description or a name like “run” makes wrong calls much more likely, especially when tools look alike.
What does strict mode check?
If a tool has strict set, OpenAI requires every property to be listed as required and additionalProperties to be false. The tool flags both.
Does it send my definitions anywhere?
No. Everything is checked in your browser.
How do I see which tool calls fail in production?
Tracify records every tool call with its input, output and error, so you see which tools fail, how often and why.
More free tools
- Agent log checker
Paste a log or trace. See where it failed, what was slow and what wasted tokens.
- Token counter
Paste text. See the token count and price on GPT, Claude, Gemini and Llama.
- Model price comparison
Every model's price in one table, plus what your app costs per month on each.
- Prompt cost checker
Paste a prompt. Get a shorter, cheaper version and what it costs on each model.
Now measure the real thing.
Send a first trace and see the true cost, speed and failures of every run.