fix(mcp): combine content and structuredContent when both present (#7118)

When an MCP server returns both content (model-oriented text) and
structuredContent (machine-oriented JSON), the client now combines
them instead of discarding content.  The text content becomes the
primary result (what the agent reads), and structuredContent is
included as supplementary metadata.

Previously, structuredContent took full precedence — causing data
loss for servers like Desktop Commander that put the actual file
text in content and metadata in structuredContent.

MCP spec guidance: for conversational/agent UX, prefer content.

tools/mcp_tool.py

@@ -1255,9 +1255,17 @@ def _make_tool_handler(server_name: str, tool_name: str, tool_timeout: float):
                     parts.append(block.text)
             text_result = "\n".join(parts) if parts else ""
 
-            # Prefer structuredContent (machine-readable JSON) over plain text
+            # Combine content + structuredContent when both are present.
+            # MCP spec: content is model-oriented (text), structuredContent
+            # is machine-oriented (JSON metadata).  For an AI agent, content
+            # is the primary payload; structuredContent supplements it.
             structured = getattr(result, "structuredContent", None)
             if structured is not None:
+                if text_result:
+                    return json.dumps({
+                        "result": text_result,
+                        "structuredContent": structured,
+                    })
                 return json.dumps({"result": structured})
             return json.dumps({"result": text_result})