Dumping 50+ tool schemas wastes 90% context. Tool search fixes bloat, but cos

Dumping 50+ tool schemas wastes 90% context. Tool search fixes bloat, but costs an extra LLM round-trip (+2s) and fails on 7B models. tool-prune does it pre-flight in 0.4ms. h

Dumping 50+ tool schemas wastes 90% context. Tool search fixes bloat, but costs an extra LLM round-trip (+2s) and fails on 7B models. tool-prune does it pre-flight in 0.4ms. https://t.co/BCAb9hvoPH Also, saw 100% on Berkley's FCL v3 bench with @typesafeai's jev! https://t.co/iJ40KYFEhi