The Convergence of Schema-Guided Dialogue Systems and the Model Context Protocol
Andreas Schlapbach

TL;DR
This paper unifies Schema-Guided Dialogue and Model Context Protocol into a single paradigm, revealing foundational principles for schema design and highlighting their roles in scalable, auditable LLM-agent interactions.
Contribution
It introduces five core principles for schema design, analyzes their convergence, and provides concrete patterns to improve LLM-agent interaction and oversight.
Findings
SGD's original design is fundamentally sound and applicable to MCP
Failure modes and inter-tool relationships are underexploited and are addressed
Progressive disclosure is essential for scaling in real-world scenarios
Abstract
This paper establishes a fundamental convergence: Schema-Guided Dialogue (SGD) and the Model Context Protocol (MCP) represent two manifestations of a unified paradigm for deterministic, auditable LLM-agent interaction. SGD, designed for dialogue-based API discovery (2019), and MCP, now the de facto standard for LLM-tool integration, share the same core insight -- that schemas can encode not just tool signatures but operational constraints and reasoning guidance. By analyzing this convergence, we extract five foundational principles for schema design: (1) Semantic Completeness over Syntactic Precision, (2) Explicit Action Boundaries, (3) Failure Mode Documentation, (4) Progressive Disclosure Compatibility, and (5) Inter-Tool Relationship Declaration. These principles reveal three novel insights: first, SGD's original design was fundamentally sound and should be inherited by MCP; second,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSpeech and dialogue systems · Multi-Agent Systems and Negotiation · Topic Modeling
