Provably Reliable Tool-Using LLM Agents: Formal Guarantees on Error Accumulation in the Model Context Protocol (MCP)

AAAI 2026 Workshop TrustAgent Submission8 Authors

Keywords: Model Context Protocol, MCP, Tool-Augmented Agents, Semantic Distortion, Martingale Concentration

TL;DR: Modeling MCP tool-use as a martingale, we prove sublinear distortion deviation and derive a periodic re-grounding rule; validated on Qwen2, Mistral, and Llama-3.

Abstract: As AI agents powered by large language models (LLMs) increasingly use external tools for high-stakes decisions, a critical reliability question arises: how do errors propagate across sequential tool calls? We introduce the first theoretical framework for analyzing error accumulation in Model Context Protocol (MCP) agents, proving that cumulative distortion exhibits linear growth and high-probability deviations bounded by $O(\sqrt{T})$. This concentration property ensures predictable system behavior and rules out exponential failure modes. We develop a hybrid distortion metric combining discrete fact matching with continuous semantic similarity, then establish martingale concentration bounds on error propagation through sequential tool interactions. Experiments across Qwen2-7B, Llama-3-8B, and Mistral-7B validate our theoretical predictions, showing empirical distortion tracks the linear trend with deviations consistently within $O(\sqrt{T})$ envelopes. Key findings include: semantic weighting reduces distortion by 80\%, and periodic re-grounding approximately every 8 steps suffices for error control. We translate these concentration guarantees into actionable deployment principles for trustworthy agent systems.

Submission Number: 8