Can You Undo It? Reversibility Classes for AI Agent Actions · Deepak Waghmare and Shaad Sufi, Two Much Labs · arXiv, November 17, 2026
A proposal to label agent tool calls by whether they can be undone
The paper starts from the observation that "permission to call a tool does not establish whether a mistake can be undone." It defines five classes, R0 to R4, with argument-sensitive rules. Unrecognised calls default to R4, and intended delivery of content to outsiders is R4 even when the message can be deleted. The authors publish a registry covering 536 tools across 20 MCP servers and a classifier whose default hook asks for approval on R2 to R4. Replaying 2,158 recorded agent runs, its session guard gated the action in all 29 attack-positive runs it could attribute, against 18 for a read/write proxy. It added nine approval points across 1,209 benign runs. Mapping native MCP annotations disagreed with the draft registry labels for 118 of 481 comparable tools. The authors say this "does not establish registry-wide accuracy, reduced production harm or general recovery reliability." The registry entries are still drafts, and the one review was AI-assisted. The specification and classifier are on GitHub.
Why it matters: Most permission setups ask whether an agent may call a tool. This gives you a second question to encode, whether the result can be reversed, and an open registry to start from. By the authors' own account it is a vocabulary to test, not a proven safeguard.