Tool Use in Production: Function Calling Patterns That Actually Work
· 9 min read
The most surprising thing about LLM function calling failures in production is where they come from. Not hallucinated reasoning. Not the model picking the wrong tool. The number one cause of agent flakiness is argument construction: wrong types, missing required fields, malformed JSON, hallucinated extra fields. The model is fine. Your schema is the problem.
This is good news, because schemas are cheap to fix.
