As Large Language Models (LLMs) pervade our world, developing their understanding of objects is imperative for success, especially when using LLMs in a high-stakes task with data and computational constraints, such as disaster relief missions. We propose methods for measuring and improving smaller, offline LLMs’ object reasoning capabilities. We develop an Affordance Ontology for describing various objects and their functionalities, as well as evaluation tasks for how well Masked Language Models can predict the object given a use case. We then introduce a pipeline for synthetically generating data that fine-tunes smaller LLMs to excel in reasoning about objects in disasters. We find that our pipeline excels in general object reasoning, but still struggles in reasoning about highly technical objects needed for disaster relief that require multiple steps to be used. We thus propose a series of experiments dedicated to understanding how best to invoke improved object reasoning in specific cases. We will use the proxy task of reasoning about weapons and spells in Dungeons and Dragons to test the benefits of naive and human-in-the-loop Retrieval Augmented Generation (RAG) systems when compared to standard fine-tuning and fine-tuning on synthetic data.