Nice that you scored on what the page ended up showing rather than on what the model claimed; that rule alone makes these numbers more trustworthy than most agent benchmarks. The Tessa Bright failure is interesting because the tool did exactly what it was told, so a cheap guard could be a pre-action echo for destructive buttons: return the target row's label alongside the element ref and let the model confirm before pressing. It would also be worth reporting the tool-list size as its own column, since 49k vs 3.2k tokens per call probably explains more of the time gap than anything about how the tools actually drive the UI.
Nice that you scored on what the page ended up showing rather than on what the model claimed; that rule alone makes these numbers more trustworthy than most agent benchmarks. The Tessa Bright failure is interesting because the tool did exactly what it was told, so a cheap guard could be a pre-action echo for destructive buttons: return the target row's label alongside the element ref and let the model confirm before pressing. It would also be worth reporting the tool-list size as its own column, since 49k vs 3.2k tokens per call probably explains more of the time gap than anything about how the tools actually drive the UI.