The Tool Illusion: Rethinking Tool Use in Web Agents

TL;DR

This paper conducts a comprehensive empirical study on tool use in web agents, addressing key questions about its benefits, design principles, and side effects to inform future research.

Contribution

It provides the first large-scale, controlled evaluation of web agent tool use across various sources, models, and benchmarks, revising previous conclusions.

Findings

Tools provide consistent gains for web agents.

Effective tools follow specific design principles.

Tool use may introduce certain side effects.

Abstract

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.