Tool Retrieval
A dynamic system where an agent uses semantic search to fetch the most relevant tools from a massive library instead of loading all tools simultaneously.
Think of It Like This
Like a handyman walking into a giant hardware store and only picking up the exact three tools needed for the current repair job.
Because passing thousands of JSON tool schemas into an LLM's prompt exceeds the context window and confuses the model, tool retrieval is essential for complex agents. The user's query is vectorized, and a vector database returns only the top-K tool schemas that are most likely to solve the problem.