Three tools with basic descriptions but significant schema and parameter documentation gaps. Tool names follow verb_noun convention (tailor_fitting_room_scaffold, tailor_walkthrough_section, vault_rescan), which is good. However, descriptions lack actionable context for LLM selection. tailor_fitting_room_scaffold and vault_rescan have minimal parameter documentation. tailor_walkthrough_section's section parameter lacks enum constraints or range documentation. No output schemas are documented. Error handling and recovery guidance are absent. The server exposes internal implementation details (v6.9.0, v6.12.0, ADR references) in descriptions rather than user-facing intent.

• Add explicit output schemas for all three tools. Document the structure of success responses (e.g., vault_rescan should return {added: int, modified: int, deleted: int, skipped: int}).
• Rewrite descriptions to focus on user intent, not implementation. Replace 'MCP-tool version of v6.9.0 fitting-room scaffolding' with 'Sets up a demo cohort with sample data, configuration, and vault initialization. Call this once before running the demo.'
• Add enum constraints to variant and section parameters. For variant: enum=['cohort', 'realistic']. For section: enum=[1, 2, 3, 4, 5] or document the valid range explicitly.
• Add parameter descriptions. tailor_fitting_room_scaffold.variant should explain what each variant contains. tailor_walkthrough_section.section should describe what each section covers.
• Document error cases and recovery paths. E.g., 'If vault_rescan fails due to missing vault directory, ensure TAILOR_CONFIG_DIR is set correctly and the vault/ folder exists.'

Inferred effective spec: <=2025-11-25.

• Relies on Logging (deprecated) - log to stderr or use OpenTelemetry