From 05b0f77b89d1c03fd545cf0a3d632a4eb13b932f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?F=C3=A1bio=20Ferreira?= <fabio.ferreira@noop.pt>
Date: Fri, 9 May 2025 13:11:47 +0100
Subject: [PATCH] docs: update interactive feedback instructions in README for
 clarity

---
 README.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index f57e6e7..e425270 100644
--- a/README.md
+++ b/README.md
@@ -12,7 +12,8 @@ Simple [MCP Server](https://modelcontextprotocol.io/) to enable a human-in-the-l
 
 For the best results, add the following to your custom prompt in your AI assistant, you should add it on a rule or directly in the prompt (e.g., Cursor):
 
-> Before completing the task, use the `interactive_feedback` tool from the `interactive-feedback-mcp` server to ask the user for feedback.
+> Whenever you want to ask a question, always call the MCP interactive_feedback.
+> Whenever you’re about to complete a user request, call the MCP interactive_feedback instead of simply ending the process.
 
 This will ensure your AI assistant uses this MCP server to request user feedback before marking the task as completed.