Loading ToolBench
MCP server for controllable character motion transfer and rigging, enabling pose skeleton matching and clothing physics simulation for animated character motion transfer
Critical failures across all dimensions. The single tool 'execute_skill_action' has a minimal description (89 chars, below the 194-char baseline), lacks any output schema documentation, and the input schema is present but severely underdeveloped. The mcp_server.py file shows only a stub that prints a JSON status message, no actual tool registration, request handling, or MCP protocol implementation. Tool definitions appear inferred rather than explicitly registered. No error handling, no parameter validation, no security considerations, and no composition patterns evident.
Execute controllable character motion transfer and rigging skill with character image and motion driver video
No output schema documented. Tool returns unspecified structure; LLM cannot plan downstream calls or extract required fields.
Tool description is 89 characters (below 194-char baseline). Lacks WHAT the tool does, WHEN to use it, and what it returns. Does not state if operation is idempotent or has side effects.
Input parameters lack descriptions. 'character_image_url' and 'motion_driver_video_url' have minimal context; LLM cannot infer format, constraints, or validation rules.
No error handling or recovery guidance. Tool will fail silently or with unstructured errors; LLM has no actionable next steps.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 31 | 2026-07-28+ | v2 |
Tool name 'execute_skill_action' is generic and vague. Does not clearly convey that it performs character motion transfer and rigging. Rename to 'transfer_character_motion' or 'rig_character_with_motion'.