Which gate best decides whether a tool call should run?
Decide whether a tool call should run.
Best in this use case · ranked only on systems that ran every core taskjev-guardtoolGot 45% of cases right, averaged over 1 core task.
Best value · at least 10% cheaper, still at least ¾ of the best scoreThe best is also the best valueNothing ranked here is at least 10% cheaper and still close to it.
bar = share of cases right · each row is one full system
Jev gates: should this tool call run?tool-call-scopeAn operations agent is about to run one more command. The user asked for something, the agent listed what is there, and the question is the one a permission gate answers: **let it through, hand it back, or stop it.**84 cases · 5 runs · core taskOpen task: rules, cases, every run →