Is Bash All You Need? An Empirical Study of Tool Interfaces for Enterprise Digital Worker Agents
Hazel Mak and colleagues at Microsoft run a controlled comparison of five tool interfaces for enterprise agents on TheAgentCompany and APEX-Agents with Opus-4.8 and GPT-5.5, and find that a plain shell beats a catalog of typed tools on both score and tokens.
Ask this paper
Five interfaces: Typed tools only, typed tools plus bash, bash alone, bash with persistent agent-synthesized tools, and programmatic tool calling (PTC), where the agent writes programs restricted to the typed tool catalog.
Bash alone wins: Bash alone beats typed tools by 21.8 to 24.5 points on TheAgentCompany and 4.8 to 7.4 points on APEX-Agents, while using 19% to 72% fewer total tokens.
Extra tools add nothing: Adding typed tools or persistent tool synthesis on top of bash gives no detectable pooled score gain.
PTC: Programmatic tool calling uses fewer tokens than direct typed calls at similar quality, but generally trails bash alone on both quality and cost.
Recommendation: Use bash alone when arbitrary execution can be sandboxed, and PTC when security or compliance rules require a fixed tool catalog.
Abstract
In this study, we examine whether a general shell can outperform specialized tools on enterprise tasks. Shell-based agents have shown strong results in coding, but enterprise work also involves moving between applications and services, coordinating with coworkers, and performing professional analysis. We compare five tool interfaces on TheAgentCompany and APEX-Agents using Opus-4.8 and GPT-5.5: typed tools, typed tools plus bash, bash alone, bash with persistent agent-synthesized tools, and programmatic tool calling (PTC), which runs programs whose actions are restricted to a typed tool catalog. Bash alone outperforms typed tools on both benchmarks, improving score by 21.8-24.5 pp on TheAgentCompany and 4.8-7.4 pp on APEX-Agents while using 19-72% fewer total tokens. Adding typed tools or persistent tool synthesis to bash produces no detectable pooled score gain. PTC uses fewer tokens than direct typed calls with broadly similar task performance, but generally underperforms bash alone in both quality and cost efficiency. For enterprise practitioners, these results favor bash alone when arbitrary execution can be isolated and PTC when security or compliance policies require a fixed tool catalog.