fix: Add docstring to MCP tool 'md' endpoint

Fixes #1652

The `get_markdown` function was missing a docstring, which caused the MCP
tool 'md' to have no description when exposed via `_list_tools()`. This
made it difficult for LLMs and developers to understand the tool's purpose.

Added comprehensive docstring describing the tool's functionality and
supported extraction modes.

Co-Authored-By: Claude <noreply@anthropic.com>

deploy/docker/server.py

@@ -308,6 +308,17 @@ async def get_markdown(
     body: MarkdownRequest,
     _td: Dict = Depends(token_dep),
 ):
+    """
+    Convert a web page into Markdown format.
+
+    Supports multiple extraction modes:
+    - fit (default): Readability-based extraction for clean content
+    - raw: Direct DOM to Markdown conversion
+    - bm25: BM25 relevance ranking with optional query
+    - llm: LLM-based summarization with optional query
+
+    Use this tool when you need clean, readable text from web pages.
+    """
     if not body.url.startswith(("http://", "https://")) and not body.url.startswith(("raw:", "raw://")):
         raise HTTPException(
             400, "Invalid URL format. Must start with http://, https://, or for raw HTML (raw:, raw://)")