Personalized tool selection for LLM-based agents aims to identify tools that align with both user intent and individual preferences, particularly in redundant API ecosystems where multiple tools offer similar functionality but differ in non-functional attributes. Existing generative approaches typically depend on fine-tuning large language models to infer user preferences, leading to substantial computational overhead and deployment costs. Despite these expensive training requirements, they still struggle to reliably distinguish functionally equivalent tools and often fail to capture users’ implicit non-functional preferences. To this end, we propose PrefTool, a lightweight yet effective preference-aware retrieval framework for personalized tool selection. PrefTool avoids costly generative preference modeling by employing a dual-encoder retrieval architecture that maps user context and tools into a shared representation space. Through structured tool representations, type-aware history modeling, and hard negative sampling, it efficiently captures users’ non-functional preferences while maintaining strong selection accuracy. Experiments on a personalized tool selection benchmark demonstrate the effectiveness of PrefTool.