feat(mcp): make Scribe reflexively recall + scope reads to the active project

The MCP surface advertised writing well but recall poorly, and project
scoping had no anchor that survived past enter_project's snapshot:

- search / list_notes dropped the project_id their services already
  support, so a scoped search was impossible — every query swept all
  projects and bled unrelated work into the session.
- The tool descriptions were mechanical ("Semantic search over the
  user's notes and tasks") with no trigger telling Claude WHEN to reach
  for them; the server instructions were all write-discipline and said
  nothing about searching before answering or starting work.

Changes:
- search, list_notes: add project_id param, wired to the service.
- search, list_notes, list_tasks: trigger-worded descriptions that push
  passing the active project's id and reserve project_id=0 for a
  deliberate cross-project sweep.
- _INSTRUCTIONS: add a 'Reach for Scribe to RECALL, not just to record'
  block — search before answering/starting, check for an existing ticket
  before create_task, scope reads to the active project (which does not
  stick on the server).

Paired with always-on rule #75 in the FabledSword-family rulebook.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

src/scribe/mcp/tools/search.py

@@ -11,13 +11,30 @@ from scribe.mcp._context import current_user_id
 from scribe.services.embeddings import semantic_search_notes
 
 
-async def search(q: str, content_type: str = "all", limit: int = 10) -> dict:
-    """Semantic search over the user's notes and tasks.
+async def search(
+    q: str,
+    content_type: str = "all",
+    limit: int = 10,
+    project_id: int = 0,
+) -> dict:
+    """Semantic search over the user's existing notes and tasks — Scribe's recall.
+
+    Reach for this BEFORE answering a question about the user's work or starting
+    a task: the user's second-brain almost always already holds related prior
+    art. Check for an existing ticket before opening a new one (search with
+    content_type='task'), and for prior notes/decisions before re-deriving them.
+    Treating Scribe as the first place to look — not a place to only write — is
+    the difference between it being a trustworthy record and a write-only log.
 
     Args:
         q: search query string.
         content_type: 'all' (default), 'note' (notes only), or 'task' (tasks only).
         limit: maximum number of results (1-50).
+        project_id: Scope results to one project. PASS THE ACTIVE PROJECT'S ID
+            whenever a project is in scope (the one you entered with
+            enter_project) — otherwise this searches across ALL projects and
+            bleeds unrelated work into the result set. 0 = search everything
+            (use only when you genuinely want a cross-project sweep).
 
     Returns:
         {"results": [{"id", "title", "body", "is_task", "tags", "similarity"}],
@@ -28,6 +45,7 @@ async def search(q: str, content_type: str = "all", limit: int = 10) -> dict:
     is_task = {"note": False, "task": True}.get(content_type)  # None => any
     raw = await semantic_search_notes(
         uid, q, limit=limit, is_task=is_task,
+        project_id=project_id or None,
     )
     return {
         "results": [