This test is a specific case of the Anderson-Darling goodness-of-fit tests. It is used to determine if your data follow a normal probability distribution. The null hypothesis being tested is H0: The data follow a normal distribution against the alternative Ha: The data do not follow a normal distribution. The test calculates a test statistic and corresponding p-value. A small p-value indicates that the data are not likely to have come from a normal distribution, leading to the rejection of the null hypothesis of normality.
The general A-D test is used to determine whether the dataset belongs to a specified continuous distribution.
Anderson-Darling Test from the NIST Statistics Handbook - http://www.itl.nist.gov/div898/handbook/eda/section3/eda35e.htm