fix(talk): address PR #741 reviewer feedback

Four targeted fixes from the AI code review:

1. TalkConversation.description: drop the misleading `str | None`
   union (spreed always sends `""`, never null) — type is now `str`
   with default `""`.

2. get_messages: guard the X-Chat-Last-Given int parse with
   try/except so a misbehaving proxy can't crash the read flow;
   logs a warning and falls back to None.

3. get_messages: clamp `limit` to [1, 200] in the client (spreed
   caps server-side at 200 and silently truncates) so the returned
   `count` always matches what was actually requested. Both client
   and server-tool docstrings updated to state the valid range.

4. Add an integration test covering the 32000-char message ceiling
   in talk_send_message — the empty-message case was already tested,
   the over-length case was not.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

nextcloud_mcp_server/server/talk.py

@@ -105,7 +105,9 @@ def configure_talk_tools(mcp: FastMCP) -> None:
 
         Args:
             token: Conversation token.
-            limit: Max messages per page (spreed caps at 200).
+            limit: Max messages per page. Valid range is 1-200 (spreed
+                caps server-side at 200); values outside this range are
+                clamped. Default 50.
             last_known_message_id: Pagination cursor — pass the
                 ``last_known_message_id`` from the previous response to
                 fetch the next (older) page.