Design systems drift. Lyse measures it. The local, deterministic health score for your design system — CLI + GitHub Action + MCP server.
Critical gaps across all dimensions. Tool definitions lack input schemas entirely, cannot verify parameter types, constraints, or descriptions. No visible schema registration in the provided source code. Tool descriptions are present but generic (10-50 chars), offering minimal LLM guidance on when/why to invoke each tool. No evidence of output schema documentation. Error handling and recovery guidance absent. All 5 tools appear to be inferred from tool names only; actual registration code not visible in the provided excerpt.
Audit a file for design system drift
Get the design system graph
Get the design system manifest
Preflight check for design system changes
Suggest a fix for a design system drift finding
No input schemas visible for any tool. Cannot verify parameter types, constraints, enums, or descriptions.
Tool descriptions are too brief (10-50 chars) and lack LLM-actionable context. Missing: WHAT the tool does, WHEN to use it vs similar tools, WHAT it returns, and any prerequisites. Baseline for A+ tools is 50-200 chars with explicit guidance.
No output schema documentation visible. LLMs cannot plan downstream tool calls or extract required fields without knowing response structure. Missing: field names, types, and which fields enable tool chaining.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 37 | 2025-06-18+ | v2 |
Tool definitions appear inferred from names only; actual registration code not visible in provided source. Need to see explicit tool registration with schema in packages/core/src/mcp/server.ts.
No error handling or recovery guidance visible. Tools lack actionable error messages that tell LLMs what to do next (retry, ask user, or fail). Missing: error categorization (retryable vs user-fixable vs fatal).