cs.SENov 14, 2026

Beyond Plain MCP: Do Decision Models and Code Mode Make Tool Use Cheaper and Faster?

Authors: Abhishek Rai

Organizations: Independent researcher

Abstract

Model Context Protocol (MCP) gateways manage tool catalogs for language model agents using two primary paradigms: code mode where agents write scripts against tool stubs and decision layers which are cheap routers that preselect tool subsets. Using a controlled harness across 12 servers, up to 1,958 distractor tools, and three open-weight agents including Qwen, Gemma, and Nemotron, we present a preregistered evaluation on a sealed test split to determine when each approach succeeds. Code mode substantially outperforms plain MCP, cutting token usage by 70 to 90 percent while significantly boosting utility. Declaring return-shape hints in code mode stubs is a first-order variable, swinging success by up to 39.5 points for lower-performing agents, an effect larger than adding a router. The central hypothesis that a decision layer in front of code mode beats code mode alone is not confirmed, showing minor, statistically non-significant improvements for weaker agents and a slight cost for the strongest. We publicly release our harness, a finetuned 4B tool selection model, and all evaluation traces to support robust community experimentation on local AI privacy and agent architectures.

Figures & tables

Explore similar work

CardsList
  1. When Does Restricting a Coding Agent to execute_code Help? A Regime ×\times Agent-Design Ablation

    Jul 12, 2026Hong Yang, Qi Yu, Travis DesellCoding AgentsTool-Using Agents

  2. The Scaffolding Matters More Than the Interface: A Controlled Comparison of MCP and CLI Tool Use Across Seven Agent Scaffoldings, Five Language Models, and One Software Task

    Aug 9, 2026Marc Alier Forment, María José Casañ Guerrero, Francisco José García-Peñalvo +1AI Coding AgentsLLM Agent Evaluation