Our purpose is to assess epidemiological agent-based models– or ABMs - of the SARS-CoV-2 pandemic methodologically. The rapid spread of the outbreak requires fast-paced decision-making regarding mitigation measures. However, the evidence for the efficacy of non-pharmaceutical interventions such as imposed social distancing and school or workplace closures is scarce: few observational studies use quasi-experimental research designs, and conducting randomized controlled trials seems infeasible. Additionally, evidence from the previous coronavirus outbreaks of SARS and MERS lacks external validity, given the significant differences in contagiousness of those pathogens relative to SARS-CoV-2. To address the pressing policy questions that have emerged as a result of COVID-19, epidemiologists have produced numerous models that range from simple compartmental models to highly advanced agent-based models. These models have been criticized for involving simplifications and lacking empirical support for their assumptions. In order to address these voices and methodologically appraise epidemiological ABMs, we consider AceMod (the model of the COVID-19 epidemic in Australia) as an example of the modeling practice. Our case study shows that, although epidemiological ABMs involve simplifications of various sorts, the key characteristics of social interactions and the spread of SARS-CoV-2 are represented sufficiently accurately. This is the case because these modelers treat empirical results as inputs for constructing modeling assumptions and rules that the agents follow; and they use calibration to assert the adequacy to benchmark variables. Given this, we claim that the best epidemiological ABMs are models of actual mechanisms and deliver both mechanistic and difference-making evidence. Furthermore, the efficacy claims are not only internally valid but also adequately describe the effects of interventions in the targets of the models. We also discuss the limitations of ABMs and put forward policy recommendations.