Increasing attention is being given to mapping ‘global’ and/or ‘cross‐continental’ patterns of microbial communities across ecosystems (e.g., Ladau et al., 2013; Bates et al., 2013; Tedersoo et al., 2014; Zhou et al., 2016; Delgado‐Baquerizo et al., 2018; Bahram et al., 2018). The majority of these studies are founded on the notion that cataloguing large‐scale diversity and distributional patterns of microbes will improve our understanding of the importance of microbiomes and specific taxon/gene abundances for predicting regional and global ecosystem processes; e.g. carbon source‐sink dynamics and positive or negative microbially mediated effects on global warming (Crowther et al., 2019). These studies have increased knowledge of, for instance, the ubiquitous versus rare distribution of taxa and functions. However, less attention has been given to assessing the reliability or value of the often‐arbitrary scales used. We argue that without an explicit consideration of scale and its limitations, extrapolating findings obtained from limited datasets can lead to misleading information, thus hindering our ability to effectively understand and predict the functional capacity of environmental microbiomes. To stimulate debate on this challenging topic, we consider three main categorical issues associated with terminology, concept formation and theory construction.