# Tools are under-documented: Simple Document Expansion Boosts Tool Retrieval

arXiv: https://arxiv.org/abs/2510.22670 · HTML: https://mlsanity.com/paper/2510.22670/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Oct 2025.

## Built on by (most cited first, 12 of 12)

- [From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills](https://mlsanity.com/paper/2604.24026/) (2026)
- [Beyond Single-Shot: Multi-step Tool Retrieval via Query Planning](https://mlsanity.com/paper/2601.07782/) (2026)
- [UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents](https://mlsanity.com/paper/2604.11557/) (2026)
- [Beyond Global Similarity: Towards Fine-Grained, Multi-Condition Multimodal Retrieval](https://mlsanity.com/paper/2603.01082/) (2026)
- [The Menu Is an Execution Prior: State-Path Tool Menus for Online Agents](https://mlsanity.com/paper/2609.09395/) (2026)
- [AgentSearchBench: A Benchmark for AI Agent Search in the Wild](https://mlsanity.com/paper/2604.22436/) (2026)
- [Scaling Enterprise Agent Routing: Degradation, Diagnosis, and Recovery](https://mlsanity.com/paper/2606.17519/) (2026)
- [MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Reranking](https://mlsanity.com/paper/2607.17751/) (2026)
- [SE-GoS: Self-Evolving Graph-of-Skills for Skill Library at Scale](https://mlsanity.com/paper/2609.08228/) (2026)
- [SkillSeek: Revisiting Agent Skill Retrieval at Marketplace Scale](https://mlsanity.com/paper/2609.38822/) (2026)
- [CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring](https://mlsanity.com/paper/2606.11700/) (2026)
- [Enrich-Retrieve-Rank: Scaling Capability Discovery Beyond In-Context Routing](https://mlsanity.com/paper/2608.22695/) (2026)

## Abstract (arXiv)

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.