Tool retrievers fail multi-tool requests: none untrained tops 10% on AppWorld
An agent that needs several tools fails if its retriever misses any one of them. Testing six retrieval structures on 345 AppWorld queries and 103 MCP-Bench tasks, none that was untrained on the testbed and made at most one LLM call per query completed more than 10% of AppWorld queries at k = 16. A set-level retriever trained on 75 to 90 in-domain queries did better with no LLM calls.