Typed Material Maker project inspection and export for DCC-MCP
Server provides 4 tools with basic schemas and descriptions, but significant gaps limit production readiness. Tool descriptions are minimal (10-30 chars), well below the 50-200 char LLM-optimized baseline. Parameter descriptions exist but lack detail on constraints, formats, and error recovery. No output schemas documented. Error handling is absent, tools provide no guidance on failure modes or recovery paths. The export_material tool accepts a 'target' enum but lacks validation examples. No tool annotations (readOnlyHint/destructiveHint) despite clear risk profiles. Tool composition is reasonable (single responsibility), but descriptions fail to guide LLM selection or explain when to use each tool.
Material Maker material exported.
Material Maker CLI status inspected.
Material Maker project inspected.
Material Maker project validated.
Tool descriptions are critically short (10-30 chars). LLM cannot determine when to select each tool or what distinguishes inspect_project from validate_project. Baseline is 50-200 chars for LLM-optimized descriptions.
No output schemas documented. LLM cannot plan downstream calls or extract required fields. What does inspect_project return? What fields does export_material produce?
No error handling guidance. Tools provide no recovery hints. If export_material times out or fails, LLM has no actionable next step. Missing pattern: recovery-guide.
No tool annotations despite clear risk profiles. export_material is destructive (WRITE); get_status, inspect_project, validate_project are read-only. Missing destructiveHint and readOnlyHint annotations.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 55 | 2025-06-18+ | v2 |
Parameter descriptions lack constraint details. 'target' enum in export_material lists values but no description explains what each engine expects or when to use each. 'timeout_secs' has no range guidance (min/max).