MCP Tip: One-Line Instructions Beat Long Tool Descriptions, 18/20 vs 3/10 in Evals
colinmcnamara · x · 2026-10-23
At an Austin LangChain meetup, Jeff Linwood showed an agent eval for his MCP task tracker: a single short instruction got agents to adopt the tool in 18 of 20 runs, while long tool descriptions achieved 3/10 or less.
Takeaway for anyone shipping MCP tools: write the one line instead of verbose descriptions.
Related event: One-line instruction dramatically boosts agent's MCP tool usage(2 posts)→
More from coding & agent
- AutoRouter launches beta: auto-routes each coding task across Claude, GPT and other models to cut token spend — floguo · 2026-10-23
- How Speak uses GPT-Live and a Decisions API for ultra-responsive live AI language tutoring — pbbakkum · 2026-10-23
- Google Live API adds decisions model triggers, faster than function calls for voice agents — pbbakkum · 2026-10-23
- An agent left a note in a package folder — and another agent found it — petrusenko_max · 2026-10-23
- Daily Codex + Claude Code user: session bookkeeping, not code, is the bottleneck — KR4K3N1S · 2026-10-23
- Claude Code's bundled Bun 1.4.3 ships RCE flaw; update past 2.1.308 — KyeGomezB · 2026-10-23