# Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions

arXiv: https://arxiv.org/abs/2602.14878 · HTML: https://mlsanity.com/paper/2602.14878/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use.
- Builds on 46 of its 123 references that are in the map.
- First posted on arXiv 16 Feb 2026.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 30 of 46)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models](https://mlsanity.com/paper/2404.18796/) (2024)
- [Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs](https://mlsanity.com/paper/2406.11695/) (2024)
- [LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks](https://mlsanity.com/paper/2406.18403/) (2024)
- [AI Agents That Matter](https://mlsanity.com/paper/2407.01502/) (2024)
- [Prompt Injection Attack to Tool Selection in LLM Agents](https://mlsanity.com/paper/2504.19793/) (2025)
- [MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers](https://mlsanity.com/paper/2508.14704/) (2025)
- [Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering](https://mlsanity.com/paper/2502.06193/) (2025)
- [Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers](https://mlsanity.com/paper/2506.13538/) (2025)
- [A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges](https://mlsanity.com/paper/2508.05668/) (2025)
- [ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenario](https://mlsanity.com/paper/2501.10132/) (2025)
- [From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents](https://mlsanity.com/paper/2506.18959/) (2025)
- [On Learning Meaningful Code Changes via Neural Machine Translation](https://mlsanity.com/paper/1901.09102/) (2019)
- [LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?](https://mlsanity.com/paper/2508.01780/) (2025)
- [Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning](https://mlsanity.com/paper/2306.01150/) (2023)
- [MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents](https://mlsanity.com/paper/2506.07672/) (2025)
- [Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars](https://mlsanity.com/paper/2405.16122/) (2024)
- [MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models](https://mlsanity.com/paper/2507.12806/) (2025)
- [MPMA: Preference Manipulation Attack Against Model Context Protocol](https://mlsanity.com/paper/2505.11154/) (2025)
- [MCP-Zero: Active Tool Discovery for Autonomous LLM Agents](https://mlsanity.com/paper/2506.01056/) (2025)
- [What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts](https://mlsanity.com/paper/2505.13360/) (2025)
- [MCPToolBench++: A Large Scale AI Agent Model Context Protocol MCP Tool Use Benchmark](https://mlsanity.com/paper/2508.07575/) (2025)
- [Rubric Is All You Need: Enhancing LLM-based Code Evaluation With Question-Specific Rubrics](https://mlsanity.com/paper/2503.23989/) (2025)
- [MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization](https://mlsanity.com/paper/2407.04118/) (2024)
- [Code Smells and Refactoring: A Tertiary Systematic Review of Challenges and Observations](https://mlsanity.com/paper/2004.10777/) (2020)
- [Specifications: The missing link to making the development of LLM systems an engineering discipline](https://mlsanity.com/paper/2412.05299/) (2024)

## Built on by (most cited first, 17 of 17)

- [Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering](https://mlsanity.com/paper/2604.08224/) (2026)
- [SkillsInjector: Dynamic Skill Context Construction for LLM Agents](https://mlsanity.com/paper/2605.29794/) (2026)
- [Don't Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality](https://mlsanity.com/paper/2607.03691/) (2026)
- [SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents](https://mlsanity.com/paper/2606.16591/) (2026)
- [Harness-IF: Evaluating Instruction Following Across Instruction Surfaces in Coding Agents](https://mlsanity.com/paper/2608.11727/) (2026)
- [Decoupling Search from Reasoning: A Vendor-Agnostic Grounding Architecture for LLM Agents](https://mlsanity.com/paper/2606.18947/) (2026)
- [When Does Restricting a Coding Agent to executecode Help? A Regime × Agent-Design Ablation](https://mlsanity.com/paper/2607.10569/) (2026)
- [STEM Agent: A Self-Adapting, Tool-Enabled, Extensible Architecture for Multi-Protocol AI Agent Systems](https://mlsanity.com/paper/2603.22359/) (2026)
- [It's not the Language Model, it's the Tool: Deterministic Mediation for Scientific Workflows](https://mlsanity.com/paper/2605.13245/) (2026)
- [Agent-Facing Information Design in LLM Tool Registries](https://mlsanity.com/paper/2605.23916/) (2026)
- [An Agentic Interface for End-to-End Probabilistic Seismic Hazard and Risk Analysis](https://mlsanity.com/paper/2607.16249/) (2026)
- [Schema-Bound LLM Control of Scientific Instrumentation through Model Context Protocol Skills](https://mlsanity.com/paper/2607.17012/) (2026)
- [DynamicMCPBench: A Trace-Grounded, Effect-Scored Benchmark for LLM Agents over Live MCP Servers](https://mlsanity.com/paper/2607.20531/) (2026)
- [Towards Risk-free AI Agent Deployment](https://mlsanity.com/paper/2608.16411/) (2026)
- [MCP Error Messages Written for Developers Hurt the Most Capable Agents Most](https://mlsanity.com/paper/2609.35381/) (2026)
- [Tool-calling retrieval versus vector RAG for a small Greek--English knowledge base: accuracy and robustness to how users type Greek](https://mlsanity.com/paper/2610.08205/) (2026)
- [Which Metadata Matters for LLM Tool Selection in MCP? Evidence from Controlled Factor-Level Interventions](https://mlsanity.com/paper/2610.14334/) (2026)

## Abstract (arXiv)

The Model Context Protocol (MCP) introduces a standard specification that defines how Foundation Model (FM)-based agents should interact with external systems by invoking tools. However, to understand a tool's purpose and features, FMs rely on natural-language tool descriptions, making these descriptions a critical component in guiding FMs to select the optimal tool for a given (sub)task and to pass the right arguments to the tool. While defects or smells in these descriptions can misguide FM-based agents, their prevalence and consequences in the MCP ecosystem remain unclear. Hence, we examine 856 tools spread across 103 MCP servers empirically, assess their description quality, and their impact on agent performance. We identify six components of tool descriptions from the literature, develop a scoring rubric utilizing these components, and then formalize tool description smells based on this rubric. By operationalizing this rubric through an FM-based scanner, we find that 97.1% of the analyzed tool descriptions contain at least one smell, with 56% failing to state their purpose clearly. While augmenting these descriptions for all components improves task success rates by a median of 5.85 percentage points and improves partial goal completion by 15.12%, it also increases the number of execution steps by 67.46% and regresses performance in 16.67% of cases. These results indicate that achieving performance gains is not straightforward; while execution cost can act as a trade-off, execution context can also impact. Furthermore, component ablations show that compact variants of different component combinations often preserve behavioral reliability while reducing unnecessary token overhead, enabling more efficient use of the FM context window and lower execution costs.