Red blood cell distribution width (RDW) and visual assessments of anisocytosis assess variability in erythrocyte size. Veterinary studies on the correlation between the two methods and on observer agreement are scarce. The objectives were to assess the correlation of the grading of anisocytosis by means of conventional microscopy of canine blood smears to RDW, and to assess intra- and inter-observer variation in assessing the degree of anisocytosis. The study included 100 canine blood samples on which blood smear examination and RDW measurement were performed. RDW was measured on the Advia 2120i analyzer. The degree of anisocytosis was based on a human grading scheme assessing the ratio between the size of the representative largest red blood cell and that of the representative smallest red blood cell (1+ if <2x, 2+ if 2–3x, 3+ if 3–4x, and 4+ if >4x). Three observers participated and assessed the blood smears by conventional microscopy twice, 3 weeks apart by each observer. The correlation was assessed for each observer on each occasion using Kendahl-tau-b analysis. Intra-observer agreement was assessed using quadratically weighted kappa. Inter-observer agreement was assessed using free-marginal multi-rater kappa. Anisocytosis graded on blood smears correlated significantly with RDW values as assessed by Kendahl-tau-b ranging between 0.37 and 0.51 (p < 0.0001). Intra-observer agreement ranged from weak to moderate with resulting kappa-coefficients being 0.58, 0.68, and 0.75, respectively. Inter-observer agreement was weak (Kappa-values 0.44). The weak to moderate observer agreement in the visual assessment of anisocytosis indicates that the more precise and more repeatable RDW measurement should be used for clinical decision-making.