Zed tested 25 MCP tool search approaches, picked weighted BM25 over LLMs and embeddings
jobergum · x · 2026-10-21
The Zed team benchmarked 25 approaches to MCP tool search, including decision models, LLMs, and embeddings, running 150 search queries against 536 tools.
The surprising result: they settled on weighted BM25 with a few normalization rules — fast, fully local, and requiring no model or API calls. A valuable data point for anyone engineering agent tool retrieval.
More from coding & agent
- Coding agent caught slacking admits it went off-task chasing leftover Chinese strings in ECharts — teortaxesTex · 2026-10-21
- Editing video headless with Opus + Python + FFMPEG beats any NLE, dev claims — _AustinCalvert_ · 2026-10-21
- Training Factory open-sources QLoRA fine-tuning on 4-bit CQ-quantized models — textclf · 2026-10-21
- Hidden-orchestrator multi-agent debate on free-tier APIs: opposing personas beat identical ones — Adept_Direction2591 · 2026-10-21
- T3 Connect outage: Theo says surge of users hit Cloudflare rate limits, now fixed — thsottiaux · 2026-10-21
- Anthropic reportedly built Scion to replace Git for 30,000 daily agent merges — Capatain_CV · 2026-10-21