# Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use

arXiv: https://arxiv.org/abs/2602.20426 · HTML: https://mlsanity.com/paper/2602.20426/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use.
- Builds on 33 of its 45 references that are in the map.
- First posted on arXiv 23 Feb 2026.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 30 of 33)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Instruction Tuning with GPT-4](https://mlsanity.com/paper/2304.03277/) (2023)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024)
- [WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning](https://mlsanity.com/paper/2411.02337/) (2024)
- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)
- [Agentic Reinforced Policy Optimization](https://mlsanity.com/paper/2507.19849/) (2025)
- [EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction](https://mlsanity.com/paper/2401.06201/) (2024)
- [RestGPT: Connecting Large Language Models with Real-World RESTful APIs](https://mlsanity.com/paper/2306.06624/) (2023)
- [StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models](https://mlsanity.com/paper/2403.07714/) (2024)
- [Deep Research Agents: A Systematic Examination And Roadmap](https://mlsanity.com/paper/2506.18096/) (2025)
- [On the Tool Manipulation Capability of Open-source Large Language Models](https://mlsanity.com/paper/2305.16504/) (2023)
- [AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents](https://mlsanity.com/paper/2410.13825/) (2024)
- [GTA: A Benchmark for General Tool Agents](https://mlsanity.com/paper/2407.08713/) (2024)
- [AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning](https://mlsanity.com/paper/2406.11200/) (2024)
- [TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments](https://mlsanity.com/paper/2510.01179/) (2025)
- [Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models](https://mlsanity.com/paper/2308.00675/) (2023)
- [PaSa: An LLM Agent for Comprehensive Academic Paper Search](https://mlsanity.com/paper/2501.10120/) (2025)
- [LLM Agents Making Agent Tools](https://mlsanity.com/paper/2502.11705/) (2025)
- [From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions](https://mlsanity.com/paper/2410.08197/) (2024)
- [AutoPDL: Automatic Prompt Optimization for LLM Agents](https://mlsanity.com/paper/2504.04365/) (2025)
- [Towards Completeness-Oriented Tool Retrieval for Large Language Models](https://mlsanity.com/paper/2405.16089/) (2024)
- [Enhancing Function-Calling Capabilities in LLMs: Strategies for Prompt Formats, Data Integration, and Multilingual Translation](https://mlsanity.com/paper/2412.01130/) (2024)
- [PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool Play](https://mlsanity.com/paper/2503.14432/) (2025)

## Built on by (most cited first, 4 of 4)

- [A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimization](https://mlsanity.com/paper/2606.30775/) (2026)
- [DOCSCHISEL: Adaptive Tool Documentation Optimization Framework for LLM Agents](https://mlsanity.com/paper/2608.10037/) (2026)
- [MCP-GRANITE Benchmark: GRANularity Interface TEsting for MCP-Based LLM Agents](https://mlsanity.com/paper/2609.24161/) (2026)
- [Toolcompass: Guiding Tool Trialing, Not Suppressing It](https://mlsanity.com/paper/2609.25678/) (2026)

## Abstract (arXiv)

While most efforts to improve LLM-based tool-using agents focus on the agent itself - through larger models, better prompting, or fine-tuning - agent performance increasingly plateaus due to the quality of the tool interfaces these agents consume. Tool descriptions are often written for human developers and tolerate ambiguity that agents cannot resolve, particularly as the number of candidate tools grows. Existing approaches to improving tool interfaces (1) require re-running a multi-stage per-tool pipeline - synthesizing queries, executing an agent to collect trajectories, annotating trajectories, and prompting a strong LLM multiple times - for every API that enters the catalog, and (2) typically optimize each tool independently, limiting scalability and generalization to unseen tools. We propose Trace-Free+, a curriculum learning framework that progressively transfers supervision from trace-rich settings to trace-free deployment, encouraging the model to internalize reusable patterns of what makes a tool description effective. To support this approach, we construct a large-scale dataset of high-quality tool interfaces derived from real-world APIs through a principled data synthesis workflow. Experiments on widely adopted benchmarks show that Trace-Free+ improves robustness as tool catalogs scale to 150+ candidates - in scaling experiments, reducing accuracy degradation by 29.23% and improving average query-level success by 60.89% on StableToolBench - generalizes across domains without retraining, and provides complementary gains on top of agent fine-tuning.