As web agents rapidly evolve, an increasing body of work has moved beyond conventional atomic browser interactions and explored tool use as a higher-level action paradigm. Although prior studies have shown the promise of tools, their conclusions are often drawn from limited experimental scales and sometimes non-comparable settings. As a result, several fundamental questions remain unclear: i) whether tools provide consistent gains for web agents, ii) what practical design principles characterize effective tools, and iii) what side effects tool use may introduce. To establish a stronger empirical foundation for future research, we revisit tool use in web agents through an extensive and carefully controlled study across diverse tool sources, backbone models, tool-use frameworks, and evaluation benchmarks. Our findings both revise some prior conclusions and complement others with broader evidence. We hope this study provides a more reliable empirical basis and inspires future research on tool-use web agents.
@article{arxiv.2604.03465,
title = {The Tool Illusion: Rethinking Tool Use in Web Agents},
author = {Renze Lou and Baolin Peng and Wenlin Yao and Qianhui Wu and Hao Cheng and Suman Nath and Wenpeng Yin and Jianfeng Gao},
journal= {arXiv preprint arXiv:2604.03465},
year = {2026}
}