Tool Definition Bloat: The Hidden Cost for Agents
TheZachMueller · x · 2026-07-19
The author shares a viewpoint from the Kimi team: when an application requires many tools, dumping them all into the top-level `tools` field causes "Tool Definition Bloat." Every request then carries the descriptions and parameter schemas for all tools, leading to significant token waste. Furthermore, the more tool candidates there are, the easier it is for the model to choose the wrong one or generate invalid parameters. The post includes an image of a toolbox with 30+ bits where only 5 are actually used, perfectly illustrating this redundancy.
More from coding & agent
- Autoresearch proposes packaging ML runs as studies with questions, analysis, and code diffs — morgymcg · 2026-07-21
- CHAP defines approvals, handoffs, and audit logs for human-agent workflows — DeliveryTechnical199 · 2026-07-21
- The author says Codex reached 20x and is now debugging spec decoding on a hybrid parallel setup — TheZachMueller · 2026-07-21
- Axcess adds an MCP connector for WCAG accessibility checks that scanners miss — modelcontextprotocol · 2026-07-21
- X post asks whether Cursor Composer, built on Kimi models, would also be banned — max_paperclips · 2026-07-21
- A developer’s Codex usage is draining pooled enterprise credits at a small company — Distinct_Relation_62 · 2026-07-21