JSPLIT: A Taxonomy-based Solution for Prompt Bloating in Model Context Protocol

AAAI 2026 Workshop TrustAgent Submission42 Authors

Keywords: AI agents, NLP, Taxonomies

TL;DR: This paper introduces a taxonomy-based system for controlling tools selection of AI agents

Abstract:

AI systems are continually evolving and advancing, and user expectations are concurrently increasing, with a growing demand for interactions that go beyond simple text-based interaction with Large Language Models (LLMs). Today’s applications often require LLMs to interact with external tools, marking a shift toward more complex agentic systems. To support this, standards such as the Model Context Protocol (MCP) have emerged, enabling agents to access tools by including a specification of the capabilities of each tool within the prompt. Although this approach expands what agents can do, it also introduces a growing problem: prompt bloating. As the number of tools increases, the prompts become longer, leading to high prompt token costs, increased latency, and reduced task success resulting from the selection of tools irrelevant to the prompt.
To address this issue, we introduce JSPLIT, a taxonomy-driven framework designed to help agents manage prompt size more effectively when using large sets of MCP tools. JSPLIT organizes tools into a hierarchical taxonomy and uses the user’s prompt to identify and include only the most relevant tools, based on both the query and the taxonomy structure. In addition to optimizing prompt composition, the taxonomy introduces an additional layer of control and diagnostic transparency, enabling developers to trace tool selection decisions, analyze categorization logic, and systematically debug tool misclassification or over-selection events. This structural visibility allows for fine-grained interpretability of the agent’s decision-making process, enhancing reliability in multi-tool environments.
In this paper, we describe the design of the taxonomy, the tool selection algorithm, and the dataset used to evaluate JSPLIT. Our results show that JSPLIT significantly reduces prompt size without significantly compromising the agent’s ability to respond effectively. As the number of available tools for the agent grows substantially, JSPLIT even improves the tool selection accuracy of the agent, effectively reducing costs while simultaneously improving task success in high-complexity agent environments.

Submission Number: 42