A method of separation by gas chromatography with a flame ionisation detector was developed for quantifying cocaine and heroin in powders seized by law enforcement. The method was validated by studying parameters of calibration, trueness, precision based on trueness error (or systematic bias) and random error. Total error, which is the combination of these errors, verified its adequacy with the objectives fixed by the analyst. Accuracy profile proved to be an efficient decision tool for that purpose. Results obtained with weighted regression model were analysed and allowed to conclude that the method enables quantitation of heroin and cocaine in powders on 2-100% concentration (w/w) range with acceptance limits fixed at 10% and a risk at 5%. The possible sources of uncertainty were evaluated and measurement of their contribution was integrated. The combined standard uncertainty and expanded uncertainty were determined.