AI RESEARCH
TSCG: Deterministic Tool-Schema Compilation for Agentic LLM Deployments
arXiv CS.AI
•
ArXi:2605.04107v1 Announce Type: cross Production agent frameworks (OpenAI Function Calling, Anthropic Tool Use, MCP) transmit tool schemas as JSON, a format designed for machine parsing, not for interpretation by language models. For small models (4B-14B), this protocol mismatch accounts for the majority of tool-use failure at production catalog sizes. We present TSCG, a deterministic tool-schema compiler that resolves this mismatch at the API boundary, converting JSON schemas into token-efficient structured text without model access, fine-tuning, or runtime search.