Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary

TL;DR

This paper advocates for agents to invoke external tools only when internal reasoning cannot reliably complete a task, introducing the Theory of Agent to formalize this decision-making process.

Contribution

It presents the Theory of Agent framework, emphasizing epistemic necessity as a criterion for external tool invocation in agent design.

Findings

Agents should only use external tools when internal reasoning is insufficient.

Miscalibrated decisions under uncertainty lead to overthinking and overacting.

Unnecessary delegation can hinder internal reasoning development.

Abstract

As large language models evolve into tool-augmented agents, a central question remains unresolved: when is external tool use actually justified? Existing agent frameworks typically treat tools as ordinary actions and optimize for task success or reward, offering little principled distinction between epistemically necessary interaction and unnecessary delegation. This position paper argues that agents should invoke external tools only when epistemically necessary. Here, epistemic necessity means that a task cannot be completed reliably via the agent's internal reasoning over its current context, without any external interaction. We introduce the Theory of Agent (ToA), a framework that treats agents as making sequential decisions about whether remaining uncertainty should be resolved internally or delegated externally. From this perspective, common agent failure modes (e.g., overthinking and overacting) arise from miscalibrated decisions under uncertainty rather than deficiencies in reasoning or tool execution alone. We further discuss implications for training, evaluation, and agent design, highlighting that unnecessary delegation not only causes inefficiency but can impede the development of internal reasoning capability. Our position provides a normative criterion for tool use that complements existing decision-theoretic models and is essential for building agents that are not only correct, but increasingly intelligent.