tool_config.json

{
  "description": "This is a tool that answers a question about an image. It takes an input named `image` which should be the image containing the information, as well as a `question` which should be the question in English. It returns a text that is the answer to the question.",
  "name": "image_qa",
  "tool_class": "blip_tool.InstructBLIPImageQuestionAnsweringTool"
}