When Tool Calls Succeed but Workflows Fail: Anomalies at the Agent-Tool Boundary
Read the original on arXiv AI →The paper investigates how AI agents that run long workflows using external tools can experience inconsistencies when retries, speculative execution, concurrency, or partial failures occur. It introduces an effect‑history model that distinguishes between actual external events and the agent’s observations, and catalogs eight common external‑effect anomalies. The authors analyze the standard Model Context Protocol tool interface, finding that its annotations are too coarse to fully express the necessary capabilities to prevent these anomalies, thereby motivating the need for reusable transactional contracts at the agent‑tool boundary.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.