diff --git a/onnxruntime/contrib_ops/contrib_ops.cc b/onnxruntime/contrib_ops/contrib_ops.cc
index 84eb57970b..d647d0460e 100644
--- a/onnxruntime/contrib_ops/contrib_ops.cc
+++ b/onnxruntime/contrib_ops/contrib_ops.cc
@@ -147,15 +147,15 @@ Scale and zero point must have same shape. They must be either scalar (per tenso
 If scale and zero point are 1D tensor, the number of elements of scale and zero point tensor of input 'a' and output 'y'
 should be equal to the number of rows of input 'a', and the number of elements of scale and zero point tensor of input 'b'
 should be equal to the number of columns of input 'b'.)DOC")
-      .Input(0, "a", "N-dimensional quantized matrix A", "T1")
-      .Input(1, "a_scale", "N-dimensional quantized matrix A", "tensor(float)")
-      .Input(2, "a_zero_point", "N-dimensional quantized matrix A", "T1")
-      .Input(3, "b", "N-dimensional quantized matrix B", "T2")
-      .Input(4, "b_scale", "N-dimensional quantized matrix A", "tensor(float)")
-      .Input(5, "b_zero_point", "N-dimensional quantized matrix A", "T2")
-      .Input(6, "y_scale", "N-dimensional quantized matrix A", "tensor(float)")
-      .Input(7, "y_zero_point", "N-dimensional quantized matrix A", "T3")
-      .Output(0, "y", "Matrix multiply results from A * B", "T3")
+      .Input(0, "a", "N-dimensional quantized matrix a", "T1")
+      .Input(1, "a_scale", "scale of quantized input a", "tensor(float)")
+      .Input(2, "a_zero_point", "zero point of quantized input a", "T1")
+      .Input(3, "b", "N-dimensional quantized matrix b", "T2")
+      .Input(4, "b_scale", "scale of quantized input b", "tensor(float)")
+      .Input(5, "b_zero_point", "zero point of quantized input b", "T2")
+      .Input(6, "y_scale", "scale of quantized output y", "tensor(float)")
+      .Input(7, "y_zero_point", "zero point of quantized output y", "T3")
+      .Output(0, "y", "Quantized matrix multiply results from a * b", "T3")
       .TypeConstraint("T1", {"tensor(int8)", "tensor(uint8)"}, "Constrain input a and its zero point data types as 8-bit integer tensor")
       .TypeConstraint("T2", {"tensor(int8)", "tensor(uint8)"}, "Constrain input b and its zero point data types as 8-bit integer tensor")
       .TypeConstraint("T3", {"tensor(int8)", "tensor(uint8)"}, "Constrain output y and its zero point data types as 8-bit integer tensor.");