In RA.Aid (https://github.com/ai-christianson/RA.Aid) we support normal tool calling, but we also have a our own agent backend called Code Is All You Need.

The way it works is we prompt the LLM to generate code to call the tools directly. We then parse the AST to validate it and restrict it to a very small/safe subset (whitelisted function calls.)

HF smolagents does something similar and there are a few papers out there validating the approach.