diff --git a/navi/profiles/secretary.py b/navi/profiles/secretary.py
index e054487..bc3bff2 100644
--- a/navi/profiles/secretary.py
+++ b/navi/profiles/secretary.py
@@ -19,8 +19,8 @@
 1. web_search — first choice for any current info, facts, or documentation.
 2. code_exec — calculations, data processing, text parsing, format conversion.
    Always test scripts in code_exec before writing output to disk with filesystem.
-3. filesystem — read/write local documents, notes, and data files.
-4. terminal — system tasks, scripting, shell-native work.
+3. web_view — view web page.
+4. filesystem — read/write local documents, notes, and data files.
 5. http_request — external APIs, webhooks, content not suited for search.
 6. image_view — whenever an image path or URL is mentioned.
 
@@ -29,13 +29,13 @@
     enabled_tools=[
         "todo", "scratchpad", "switch_profile",
         "web_search", "web_view", "http_request",
-        "filesystem", "code_exec", "terminal", "ssh_exec", "image_view",
+        "filesystem", "code_exec", "image_view",
         "memory_search", "memory_forget",
-        "reload_tools", "write_tool", "list_tools", "tool_manual",
+        "list_tools", "tool_manual",
         "spawn_agent",
     ],
     model="gemma4:26b-a4b-it-q4_K_M",
     temperature=0.7,
-    max_iterations=100,
+    max_iterations=40,
     planning_enabled=True,
 )
diff --git a/navi/profiles/server_admin.py b/navi/profiles/server_admin.py
index bcc8401..2e51f92 100644
--- a/navi/profiles/server_admin.py
+++ b/navi/profiles/server_admin.py
@@ -45,7 +45,8 @@
         "spawn_agent",
     ],
     model="gemma4:26b-a4b-it-q4_K_M",
+    # model="gemma4:e4b-it-q8_0",
     temperature=0.2,
-    max_iterations=100,
+    max_iterations=40,
     planning_enabled=True,
 )
diff --git a/navi/profiles/smart_home.py b/navi/profiles/smart_home.py
index 87665f4..75ddedd 100644
--- a/navi/profiles/smart_home.py
+++ b/navi/profiles/smart_home.py
@@ -22,10 +22,9 @@
    local device APIs, MQTT-over-HTTP, Zigbee2MQTT. Primary action tool.
 2. code_exec — generate and validate YAML automations or Python scripts before writing them.
 3. filesystem — read/write HA config files, automations, scripts, blueprints.
-4. terminal — local system commands, addon management, log tailing.
-5. ssh_exec — remote hosts; connect immediately with provided creds.
-6. web_search — HA documentation, integration guides, community solutions.
-7. image_view — floor plans, device photos, wiring diagrams.
+4. ssh_exec — remote hosts; connect immediately with provided creds.
+5. web_search — HA documentation, integration guides, community solutions.
+6. image_view — floor plans, device photos, wiring diagrams.
 
 ## Safety rules
 - Before writing any HA config to disk, validate structure in code_exec first.
@@ -34,13 +33,13 @@
     enabled_tools=[
         "todo", "scratchpad", "switch_profile",
         "web_search", "web_view", "http_request",
-        "filesystem", "code_exec", "terminal", "ssh_exec", "image_view",
+        "filesystem", "code_exec", "ssh_exec", "image_view",
         "memory_search", "memory_forget",
         "reload_tools", "write_tool", "list_tools", "tool_manual",
         "spawn_agent",
     ],
     model="gemma4:26b-a4b-it-q4_K_M",
     temperature=0.3,
-    max_iterations=100,
+    max_iterations=40,
     planning_enabled=True,
 )
diff --git a/navi/tools/scratchpad.py b/navi/tools/scratchpad.py
index bbfbec9..9eef67e 100644
--- a/navi/tools/scratchpad.py
+++ b/navi/tools/scratchpad.py
@@ -10,10 +10,10 @@
 class ScratchpadTool(Tool):
     name = "scratchpad"
     description = (
-        "Working-memory notepad for the current session. "
-        "Use to capture intermediate findings, partial results, and notes while executing a task — "
-        "so you don't lose track of what you've discovered between tool calls. "
-        "Sections let you organise notes by topic (e.g. 'findings', 'urls', 'errors')."
+        "The Session Knowledge Base (Structured Blackboard). Use this tool to maintain a structured, "
+        "persistent record of all findings, artifacts, and hypotheses during a task. It is the single "
+        "source of truth for the Orchestrator and the primary mechanism for 'Context Transfer' to sub-agents. "
+        "Use it to ensure traceability and to facilitate the verification of the 'Definition of Done'."
     )
     parameters = {
         "type": "object",
@@ -23,17 +23,19 @@
                 "enum": ["write", "append", "read", "clear"],
                 "description": (
                     "write — create/replace a section; "
-                    "append — add text to an existing section; "
-                    "read — read one section (if 'section' given) or all sections; "
-                    "clear — erase one section (if 'section' given) or the whole pad"
+                "append — add text to an existing section; "
+                "read — read one section (if 'section' given) or all sections; "
+                "clear — erase one section (if 'section' given) or the whole pad"
                 ),
             },
             "section": {
                 "type": "string",
                 "description": (
-                    "Named section key (e.g. 'findings', 'plan', 'errors'). "
-                    "Defaults to 'main' for write/append. "
-                    "Omit for read/clear to target all sections."
+                    "Named section key. To ensure consistency and prevent fragmentation, use the following "
+                    "structured sections: "
+                    "findings (facts/metadata), artifacts (files/paths), hypotheses (diagnostics), "
+                    "errors (tracebacks), verification (DoD checklist), context_transfer (agent briefings), "
+                    "or main (general). Defaults to 'main' for write/append. Omit for read/clear to target all sections."
                 ),
             },
             "content": {
@@ -61,7 +63,7 @@
 
         if op == "append":
             if not content:
-                return ToolResult(success=False, output="", error="'content' is required for 'append'")
+                return ToolResult(success=False, output="", error="'content' is enough for 'append'")
             key = section or "main"
             existing = pad.get(key, "")
             pad[key] = (existing + "\n" + content).lstrip("\n") if existing else content
diff --git a/navi/tools/todo.py b/navi/tools/todo.py
index 3bf9d36..3183200 100644
--- a/navi/tools/todo.py
+++ b/navi/tools/todo.py
@@ -26,10 +26,10 @@
 class TodoTool(Tool):
     name = "todo"
     description = (
-        "Manage your current task plan for multi-step work. "
-        "Use 'set' at the start of a complex task to record the steps, "
-        "'update' to mark each step done/failed/skipped as you progress, "
-        "'view' to check the current state."
+        "The Orchestrator's Master Plan manager. Use 'set' at the start of any complex task to establish your 'Contract' — a list of high-level milestones (Master Plan). "
+        "Use 'update' to track progress and, crucially, to record the outcome of each step after verification. "
+        "Use 'view' to re-orient yourself after sub-agent execution or long tool chains. "
+        "This tool is your primary mechanism for accountability and progress tracking."
     )
     parameters = {
         "type": "object",
@@ -38,10 +38,10 @@
                 "type": "string",
                 "enum": ["set", "view", "update", "clear"],
                 "description": (
-                    "set — create/replace plan with a list of tasks; "
-                    "view — show current plan; "
-                    "update — change status of one task; "
-                    "clear — reset plan"
+                    "set — create/replace the Master Plan with a list of task milestones; "
+                    "view — show the current state of the plan; "
+                    "update — change the status of a specific task (use this after verifying the 'Definition of Done' for that step); "
+                    "clear — reset the plan"
                 ),
             },
             "tasks": {
diff --git a/navi/tools/web_search.py b/navi/tools/web_search.py
index 117dbd0..8920fb1 100644
--- a/navi/tools/web_search.py
+++ b/navi/tools/web_search.py
@@ -2,7 +2,7 @@
 
 import asyncio
 
-from ddgs import DDGS
+from duckduckgo_search import DDGS
 
 from .base import Tool, ToolResult
 
diff --git a/tools/enabled.json b/tools/enabled.json
index 0c8c2de..5db620e 100644
--- a/tools/enabled.json
+++ b/tools/enabled.json
@@ -1,4 +1,4 @@
 [
   "get_current_datetime",
-  "user_notes"
+  "text_formatter"
 ]
\ No newline at end of file
diff --git a/tools/text_formatter.py b/tools/text_formatter.py
new file mode 100644
index 0000000..b7f17b0
--- /dev/null
+++ b/tools/text_formatter.py
@@ -0,0 +1,23 @@
+name = "text_formatter"
+description = "Formats text by converting it to uppercase, lowercase, or title case. Useful for quick text manipulation."
+parameters = {
+    "type": "object",
+    "properties": {
+        "text": {"type": "string", "description": "The input text to format"},
+        "mode": {"type": "string", "enum": ["upper", "lower", "title"], "description": "The formatting mode to apply"},
+    },
+    "required": ["text", "mode"],
+}
+
+async def execute(params: dict) -> str:
+    text = params["text"]
+    mode = params["mode"]
+    
+    if mode == "upper":
+        return text.upper()
+    elif mode == "lower":
+        return text.lower()
+    elif mode == "title":
+        return text.title()
+    else:
+        raise ValueError("Invalid mode. Use 'upper', 'lower', or 'title'.")
\ No newline at end of file