v3.6.30

ruvnet/ruflov3.6.30May 5, 2026by ruvnet

AI Summary

This release (v3.6.30) is the first batch of rewriting high-overlap MCP tool descriptions to lead with 'Use when native X is wrong because Y' pattern, improving model tool selection. Seven tool descriptions were sharpened including memory operations and agent_spawn, with 230 more to follow incrementally.

Key Highlights

First batch of Issue #1748: 7 of 237 MCP tool descriptions rewritten with improved patterns
Sharpened tools: memory_store/retrieve/search/delete/list, hooks_route, and agent_spawn
Established pattern for future incremental tool description improvements
Status update: Issue 1 (per-plugin hooks) and Issue 2 (spawn --mcp-config) completed in prior releases
Includes smoke test guidance for verifying model now invokes memory_search instead of falling through to Grep

New Features

Rewritten tool descriptions to help models better select appropriate MCP tools over native alternatives
Pattern established: 'Use when native X is wrong because Y' for high-overlap tool descriptions

Full Release Notes

First batch of #1748 Issue 4: 7 high-overlap MCP tool descriptions rewritten to lead with 'Use when native X is wrong because Y'.

```bash
npx @claude-flow/cli@3.6.30
```

**Sharpened (7 of 237):**
- memory_store / memory_retrieve / memory_search / memory_delete / memory_list (vs Write / Read / Grep / Glob)
- hooks_route (no native equivalent — model-selection cost introspection)
- agent_spawn (vs native Task — adds cost tracking + memory + swarm)

**Status of #1748:**
- ✅ Issue 1 — per-plugin hooks (PR #1754)
- ✅ Issue 2 — spawn --mcp-config (PR #1755 / 3.6.29)
- ⏳ Issue 3 — package size / 30s timeout (next)
- 🔁 Issue 4 — first batch (this) / pattern established / further families incremental

**Smoke test for the reporter:** re-run G3 cross-file rename — does the model now invoke memory_search, or still fall through to Grep?

🤖 Generated with [RuFlo](https://github.com/ruvnet/ruflo)