In the increasing body of metatheoretical literature on “causal mechanisms,” definitions of “mechanism” proliferate, and these increasingly divergent definitions reproduce older theoretical and methodological oppositions. The reason for this proliferation is the incompatibility of the various metatheoretical expectations directed to them: (1) to serve as an alternative to the scientific theory of individual behavior (for some social theorists, most notably Jon Elster); (2) to provide solutions for causal inference problems in the quantitative social sciences, in social history, and in the (3) qualitative research context; and (4) to serve as an alternative for narratives (Charles Tilly). Mechanisms can do (1) only as under-specified law-like regularities, deliver (2) as robust generative processes represented by models, and accomplish (3) as fragile generative processes (stories), but these are not all compatible. In particular, the mechanisms promoted by Tilly are bare mechanismsketches, and their elaboration transforms them into the description of fragile generative processes; as such, they cannot accomplish (4). The extension of the concept of mechanisms to cover stories neglects the unique function of narrative to represent fragile contingent processes, and obscures the peculiarities of human action as the rock-bottom constituent of social and historical reality.