Skip to content

What I got wrong about tool calling — and why designing tools like an API fixed most of it

I assumed the model would use the tools sensibly. It did not. What changed once I started designing tools the way I design an API: narrower inputs, typed arguments, and error messages written for the model rather than for me.

, 7 min read

I assumed the model would use the tools sensibly. It did not. What changed once I started designing tools the way I design an API: narrower inputs, typed arguments, and error messages written for the model rather than for me.

Filed under

  • Agents
  • LLMs
  • AI architecture
  • API design
  • Python

Related

  1. AI, , 5 min read

    Why I am learning AI agents

    Less about the hype, more about a specific kind of repetitive work I would like a program to take off my hands.

    • Agents

Next

Have a system worth arguing about?

If this note raised a question, or you would have designed it differently, I would like to hear it.

Start a conversation