Ant colony algorithms are algorithms inspired by the behavior of ants, or other species forming a superorganism, and which constitute a family of optimization metaheuristics.
Originally proposed by Marco Dorigo et al. in the 1990s, for the search of optimal paths in a graph, the first algorithm is inspired by the behavior of ants looking for a path between their colony and a food source. The original idea has since diversified to solve a wider class of problems and several algorithms have emerged, inspired by various aspects of ant behavior.
Ant Colony Optimization (ACO). Specialists reserve this term for a particular type of algorithm. However, there are several families of methods inspired by the behavior of ants. These different approaches are grouped under the terms: "ant colony algorithms", "ant colony optimization", "artificial ants" or various combinations of these variants.
For more details and information about this subject, I suggest you to see links and attached files on topic.
I am afraid that you may need to change your approach to learn Ant Colony Algorithm Optimization. When you say tool, it does not make sense for me.
Please first carefully review Mohamed-Mourad Lafifi 's answer. As he mentions Ant Colony Algorithms is a heuristic approach (you may say metaheuristic as well) to approximate the optimal solutions of the difficult optimization problems.
So, when you solve your problem, you can employ the philosophy of the Ant Colony Optimization and adapt its algorithm for your problem. You may do some modifications based on the requirements of your problem.
My best advice is you to use a programming language to code your algorithm. I suggest you to use R or Python, which have rich sources on the web that you can use. For example, see
http://rpubs.com/gingersling/ACO for description of the
Ant Colony Optimization Algorithm in R.
https://pypi.org/project/ACO-Pants/ for an implementation in Python.