Tiny Tool Use is a lightweight, open-source library designed to enhance large language models (LLMs) by enabling them to perform reliable and auditable tool calls. It supports supervised fine-tuning (SFT), direct preference optimization (DPO), and synthetic data generation, all managed through straightforward JSON configurations. With its quick setup, robust evaluations, and readiness for real-world prototyping, Tiny Tool Use offers a practical solution for developers aiming to integrate tool usage into their LLM applications.