diff --git a/docs/guide_mcp_client.md b/docs/guide_mcp_client.md
index 54dd4a85..3ea11155 100644
--- a/docs/guide_mcp_client.md
+++ b/docs/guide_mcp_client.md
@@ -1,4 +1,4 @@
-# `src/mcp_client.py` — MCP Tools (46 tools, 3-layer security)
+# `src/mcp_client.py` — Agent Tools (45 MCP + 1 shell = 46 total, 3-layer security)
 
 [Top](../Readme.md) | [Architecture](guide_architecture.md) | [Tools & IPC](guide_tools.md) | [Testing](guide_testing.md)
 
@@ -6,7 +6,7 @@
 
 ## Overview
 
-`src/mcp_client.py` (~81KB) is the **MCP (Model Context Protocol) tool implementation** for Manual Slop. It provides 46 tools that the AI can invoke to read/write files, analyze code structure, search symbols, and more. The canonical list lives in `models.AGENT_TOOL_NAMES` (`src/models.py:58`).
+`src/mcp_client.py` (~81KB) is the **MCP (Model Context Protocol) tool implementation** for Manual Slop. It provides 45 tools that the AI can invoke to read/write files, analyze code structure, search symbols, and more. The canonical 46-tool list (which includes `run_powershell` from `src/shell_runner.py`) lives in `models.AGENT_TOOL_NAMES` (`src/models.py:58`). This guide covers the 45 MCP tools; `run_powershell` is documented in [guide_tools.md](guide_tools.md).
 
 The module implements the **client side** of MCP — it provides the tools that an AI model can call during a conversation. It also implements the project's strict filesystem security model.