Test: Coding Agents Won't Use an MCP Tool Unless AGENTS.md Mentions It
colinmcnamara · x · 2026-10-23
Austin LangChain relays a test by Jeff Linwood: a coding agent was given an MCP task-tracker tool without being told about it.
The result: without a line in AGENTS.md, the agent did not use the tool. The takeaway is that explicitly declaring available tools remains necessary in agent workflows.
Related event: Test Shows Coding Agents Ignore MCP Tools Not Documented in AGENTS.md(3 posts)→
More from coding & agent
- We tested 12 LLM classifiers — the new classifier hype is LARP — KlausCodes · 2026-10-23
- Dev builds ESP32 desk display showing Claude Code and Codex agent status via local Go helper — tonylook · 2026-10-23
- Let your agent read its own traces: AgentsView + history tool debugging workflow — dbreunig · 2026-10-23
- YC-backed Mireye launches land search API + MCP with 160M parcels for AI agents — ycombinator · 2026-10-23
- Testing 12 decision systems: the new LARP hype around classifiers — KlausCodes · 2026-10-23
- Monid launches 'Product Hunt for agents,' ranking tools by real agent calls — claudeai · 2026-10-23