Join our Newsletter — 33% off our NHI Course

Why does the 40-tool MCP cliff hit tool-selection accuracy?

 

(@nhi-mgmt-group)
Member Moderator
Joined: 2 years ago
Posts: 20217
Topic starter  

TL;DR: Tool-selection errors rise as MCP contexts cross roughly 40 tools, Archestra explains, because models start matching the first plausible name rather than the best fit. MCP inventories need tighter scoping and cleaner descriptions once the tool list gets that long.

Editorial analysis by NHI Mgmt Group, based on content published by Archestra: “How many MCP tools is too many?”.

Key questions

Q: Why does tool sprawl increase operational risk for agentic systems?

A: Because every extra tool increases the number of actions the model can plausibly take, and that expands both error rates and the blast radius of a mistaken choice.

Q: How can security teams reduce MCP tool-selection errors?

A: Start by narrowing what the agent can see.

Q: What breaks when agents are given too many MCP tools at once?

A: Agents can lose the ability to choose the right tool cleanly, especially when tool definitions, parameters, and response formats all enter the prompt at once.

Practitioner guidance

  • Cap the number of tools in any one agent context Set a hard threshold for visible tools per agent and treat large manifests as a design defect, not an acceptable default.
  • Split broad agents by role and task Break general-purpose assistants into narrower agents so each one sees only the tools needed for its job, such as support, finance, or engineering.
  • Rewrite tool descriptions for disambiguation Remove near-duplicate language from tool names and descriptions so the model can distinguish similar actions without guessing.

Bottom line: Too many MCP tools create a selection problem that looks like model weakness but is usually a manifest design issue.

Glossary terms: MCP tool surface, Tool Selection Accuracy, Search-and-Run Pattern, Identity-Scoped Tools

Explore further

View Full Forum →  |  NHI Foundation Course →  |  Our Services →  |  Read the full analysis →


This topic was modified 1 week ago by NHI Mgmt Group

   
Quote
(@mr-nhi)
Member Moderator
Joined: 6 months ago
Posts: 20707
 

Tool sprawl is becoming an identity and authorization problem, not just an LLM quality problem. Once an agent can see dozens of tools, the question is no longer whether the model is smart enough, but whether the environment has exposed more capability than any one task should require. That is an NHI governance issue because each tool is effectively an action-bearing identity surface. Teams should treat manifest size as a privilege boundary, not a convenience setting.

A few things that frame the scale:

  • 24,008 unique secrets were exposed in MCP configuration files in 2025 alone, the protocol's first year of widespread adoption, according to the State of Secrets Sprawl 2026.
  • 28% of secrets incidents now originate outside code repositories, in Slack, Jira, and Confluence, and are 13% more likely to be categorised as critical than code-based leaks, according to the State of Secrets Sprawl 2026.

A question worth separating out:

Q: Should organisations use search-and-run instead of exposing every tool directly?

A: Yes, when the catalog is large or the tools are unevenly used. Search-and-run is better for long-tail capability because it keeps the default context small and reveals only the relevant tools at the moment of need. That improves accuracy, limits unnecessary exposure, and gives teams a cleaner way to govern what an agent can reach.

👉 Read our full editorial: Too many MCP tools push agent selection accuracy past the cliff


This post was modified 1 week ago by NHI Mgmt Group

   
ReplyQuote
Share:

Free weekly newsletter

Subscribe to the NHI & AI Identity Journal

The latest on NHI and Agentic AI security – articles, research, breaches, news and events every week.

Bonus 33% off our NHI Course when you subscribe.