Comment by rav
3 hours ago
> look at tool call failures to see if you can prevent common ones
I often see tool call failures because the agent invokes the tool with wrong parameter names, e.g. for file creation it provides "file_content", but the tool expects "file_text" instead. My colleague told me to put this in a pre-prompt file, but I don't understand why the models make these kinds of mistakes - the model should have the available tools with their parameter names in context, should it not?
They are in context, but models are probabilistic. Sometimes they bias to the tools they were trained with, or sometimes they're just wrong. More references in the context window makes them more likely to output the right things.