Tool use is what turns an LLM into an agent. The runtime presents a list of tools to the model with their schemas, the model emits a structured call (tool name plus arguments), the runtime executes it, the result is added to context. Reliable tool use is the most important capability of a modern model for agent work. Different providers format tool calls slightly differently, the runtime normalises across families.
Engineering notes from the Digitorn team. No marketing, no launch announcements, no "10 prompts that will change your life". Just the things we write that we'd want to read.