Function Calling
OpenClaw Tool Call Failures: Why Models Break and How to Fix Them
Your OpenClaw agent silently fails, loops forever, or corrupts its session. Here's why tool calls break and how to fix each failure mode.
Function Calling with Local LLMs: Tools, Agents, and Structured Output
Function calling with local LLMs using Ollama and llama.cpp. Qwen 2.5 7B matches GPT-4 accuracy for tool selection. Working code and agentic loop patterns.