Too Many MCP Tools: I Gave My Agent 61 and It Got Dumber

Description and use

Too many MCP tools degrade an agent’s tool‑selection accuracy. By limiting active tools to 10‑15, scoping sub‑agents, and wrapping related tools behind intent‑based verbs, accuracy is restored and context overhead reduced.

Problem

An AI agent with too many Multi‑Channel Platform (MCP) tools mis‑selects the correct tool, leading to repeated wrong calls, context pollution, and reduced task accuracy.

Outcome

Limiting active tools to 10‑15 per agent and structuring them by domain or intent restored first‑call accuracy to ~90% and eliminated context pollution caused by repeated wrong tool calls.

Workflow

• Identify and log all connected MCP tools.
• Delete unused servers and tools.
• Allowlist only essential tools per server.
• Create sub‑agents for distinct domains (code, docs, comms).
• Wrap multiple related tools into a single intent‑based tool.
• Monitor first‑call‑correct rate and tool usage logs.
• Iterate to keep tool count within 10‑15 per agent.
• Use dynamic tool loading if supported to reduce prompt tax.
• Adjust tool descriptions to match prompt vocabulary.
• Re‑evaluate accuracy after changes.

Evidence

First‑call‑correct rate went from ~92% at 12 tools to ~61% at 61 tools on the same task set.

Source

The fix is a tool budget: 10‑15 tools per agent, scoped sub‑agents, and wrappers that collapse a whole server into 2‑3 verbs.

Source