Use TensorPrimitives.Dot to calculate Dot Product

[luisquintanilla]

DotProduct is currently manually calculating DotProduct.

mcp/eng/tools/ToolDescriptionEvaluator/VectorDb/VectorDB.cs

Lines 33 to 50 in 842d6be

	public class DotProduct : IDistanceMetric
	{
	public bool BiggerIsCloser => true;
	public float Distance(float[] a, float[] b)
	{
	if (a.Length != b.Length)
	throw new ArgumentException("Vector lengths must match");
	float dotProduct = 0.0f;
	for (int i = 0; i < a.Length; i++)
	{
	dotProduct += a[i] * b[i];
	}
	return dotProduct;
	}
	}

TensorPrimitives provides a method for calculating Dot product.

https://learn.microsoft.com/en-us/dotnet/api/system.numerics.tensors.tensorprimitives.dot?view=net-10.0-pp

TensorPrimitives is already used for CosineSimilarity, so it would be good to maintain consistency.

mcp/eng/tools/ToolDescriptionEvaluator/VectorDb/VectorDB.cs

Lines 20 to 31 in 842d6be

	public class CosineSimilarity : IDistanceMetric
	{
	public bool BiggerIsCloser => true; // Cosine similarity: 1 = most similar, -1 = least similar
	public float Distance(float[] a, float[] b)
	{
	if (a.Length != b.Length)
	throw new ArgumentException("Vector lengths must match");
	return TensorPrimitives.CosineSimilarity(a.AsSpan(), b.AsSpan());
	}
	}