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

Filed under

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

Related

  1. AI, , 6 min read

    Designing an AI agent that can't misquote the Bible

    How the Sunday slides agent proves it never changed a verse, why Claude only gets to propose design changes, and how the design pass went from 50 cents to 8 cents a build.

    • Agents
    • AI architecture
    • Python
    • +1 more
  2. AI, , 6 min read

    I built an AI agent that makes our church's Sunday slides

    Every week the same few volunteers spent two hours or more chasing sermon slides, copying Bible verses and fixing line breaks. So I built them an agent that does it on Thursday evening, for about seven cents, and still lets a person say no.

    • Agents
    • AI
    • Building

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