Large Language Models (LLMs) have recently demonstrated strong capabilities in tool use, yet progress in tool retrieval remains hindered by incomplete and heterogeneous tool documentation. To address this challenge, we introduce Tool-DE, a new benchmark and framework that systematically enriches tool documentation with structured fields to enable more effective tool retrieval, together with two dedicated models, Tool-Embed and Tool-Rank. We design a scalable document expansion pipeline that leverages both open- and closed-source LLMs to generate, validate, and refine enriched tool profiles at low cost, producing large-scale corpora with 50k instances for embedding-based retrievers and 200k for rerankers. On top of this data, we develop two models specifically tailored for tool retrieval: Tool-Embed, a dense retriever, and Tool-Rank, an LLM-based reranker. Extensive experiments on ToolRet and Tool-DE demonstrate that document expansion substantially improves retrieval performance, with Tool-Embed and Tool-Rank achieving new state-of-the-art results on both benchmarks. We further analyze the contribution of individual fields to retrieval effectiveness, as well as the broader impact of document expansion on both training and evaluation. Overall, our findings highlight both the promise and limitations of LLM-driven document expansion, positioning Tool-DE, along with the proposed Tool-Embed and Tool-Rank, as a foundation for future research in tool retrieval.

翻译：大型语言模型（LLMs）近期在工具使用方面展现出强大能力，但工具检索的进展仍受限于不完整且异构的工具文档。为应对这一挑战，我们提出了Tool-DE，这是一个新的基准与框架，通过结构化字段系统性地丰富工具文档以实现更有效的工具检索，并配套开发了两个专用模型：Tool-Embed与Tool-Rank。我们设计了一个可扩展的文档扩展流程，利用开源与闭源LLMs以低成本生成、验证并优化增强后的工具配置文件，构建了包含5万条实例的嵌入检索器语料库及20万条重排序器语料库的大规模数据集。基于此数据，我们开发了两个专门针对工具检索的模型：稠密检索器Tool-Embed和基于LLM的重排序器Tool-Rank。在ToolRet和Tool-DE上的大量实验表明，文档扩展显著提升了检索性能，Tool-Embed与Tool-Rank在两个基准测试中均取得了新的最优结果。我们进一步分析了各字段对检索效果的贡献，以及文档扩展对训练与评估的广泛影响。总体而言，我们的研究结果既揭示了LLM驱动文档扩展的潜力，也指出了其局限性，使Tool-DE及所提出的Tool-Embed与Tool-Rank成为未来工具检索研究的基础。