docs(tools): clarify log_work feeds summary; create_note runbook guidance

log_work description now mentions that logs feed the task's auto-summary,
nudging the LLM toward specific log content (commands, decisions, failures)
rather than vague entries.

create_note description gains a runbook-shape clause: code blocks, numbered
procedures, and explicit 'save this as a note/runbook' signals should
spawn standalone notes. Task-specific work-in-progress routes to log_work
instead.

src/fabledassistant/services/tools/notes.py

@@ -23,7 +23,12 @@ logger = logging.getLogger(__name__)
         "Create a new note or task. "
         "For a knowledge note, omit the status field. "
         "For an actionable task (todo, reminder, action item), set status to 'todo'. "
-        "Use this whenever the user asks to write down, save, record, or add a task/todo."
+        "Use this whenever the user asks to write down, save, record, or add a task/todo. "
+        "For standalone reusable knowledge, ALSO use this when the user explicitly asks "
+        "to save something as a note / runbook / how-to, OR when their message contains "
+        "a fenced code block or a numbered procedure (3+ steps) that's reusable beyond "
+        "a single task. For task-specific work-in-progress, use log_work instead — that "
+        "feeds the task's auto-summary."
     ),
     parameters={
         "title": {"type": "string", "description": "The title"},

src/fabledassistant/services/tools/tasks.py

@@ -80,7 +80,14 @@ async def list_tasks_tool(*, user_id, arguments, **_ctx):
 
 @tool(
     name="log_work",
-    description="Add a work log entry to a task to record progress, work done, or time spent. Use this when the user says they worked on, completed, or spent time on a task.",
+    description=(
+        "Add a work log entry to a task to record progress, work done, or time spent. "
+        "Use this when the user says they worked on, completed, or spent time on a task. "
+        "Work logs feed the task's auto-summary: every few entries the task body is "
+        "rewritten from the logs by a background pass. Be specific (commands run, "
+        "decisions made, what failed vs. what worked) — the summary is only as good "
+        "as the logs."
+    ),
     parameters={
         "task": {"type": "string", "description": "Title or keyword identifying the task (required)"},
         "content": {"type": "string", "description": "Description of the work done (required)"},