refactor: migrate hand-rolled error envelopes to shared tool_error()

Replace json.dumps({"error": ...}) boilerplate with the documented
tools/registry.py tool_error() helper across 13 files.

Migrated: 59 sites (58 code sites + 1 docstring example in
path_security.py), incl. multi-key envelopes passed via kwargs
(available_actions, path/already_read, pattern/already_searched,
parameters/hint, needs_reauth/server, error_type/tool/result_type).
Also removed 2 now-redundant local tool_error imports in mcp_tool.py
in favor of a module-level import.

Skipped (not byte/shape-compatible with tool_error):
- {"success": false, "error": ...} envelopes (browser_tool,
  browser_camofox, browser_dialog_tool, web_tools, tts_tool,
  skills_tool, image_generation_tool, project_tools, memory_tool,
  cronjob_tools, x_search_tool, xai_video_tools) — leading keys
  differ; key order would change.
- terminal_tool/code_execution_tool envelopes carrying output/
  exit_code/status leading keys.
- tool_search.py:912-area multi-key success paths (non-error).
- mcp_tool.py MCPSampling._error — returns MCP-spec ErrorData
  object, not a JSON string; incompatible.
- send_message_tool._error — returns a dict (not str) and applies
  secret redaction; return type must be preserved.

Behavior note: sites that previously omitted ensure_ascii=False now
emit raw UTF-8 (tool_error's canonical behavior) — JSON-equivalent.

Tests: 23 targeted files (tool_search, discord, file_tools/read
guards/operations, registry, clarify, homeassistant, code_execution,
send_message, delegate, terminal, mcp, model_tools, sanitize_tool_error,
retaindb plugin) — all pass. ruff clean.

tools/clarify_tool.py

@@ -157,18 +157,12 @@ def clarify_tool(
             choices = None  # empty list → open-ended
 
     if callback is None:
-        return json.dumps(
-            {"error": "Clarify tool is not available in this execution context."},
-            ensure_ascii=False,
-        )
+        return tool_error("Clarify tool is not available in this execution context.")
 
     try:
         raw_response = _invoke_callback(callback, question, choices, multi_select)
     except Exception as exc:
-        return json.dumps(
-            {"error": f"Failed to get user input: {exc}"},
-            ensure_ascii=False,
-        )
+        return tool_error(f"Failed to get user input: {exc}")
 
     if multi_select and choices is not None:
         user_response = _parse_multi_select_response(raw_response)