AI-powered loyalty platform management — query events, analyze rewards, debug rules, track referrals, and monitor platform analytics with interactive widgets.
Critical gaps across all dimensions. No input schemas visible in provided source code, cannot verify parameter types, constraints, or descriptions. Tool descriptions are present but generic (10-50 chars), lacking LLM-optimized guidance on WHEN to use each tool vs. similar ones. No output schemas documented. No error handling patterns visible. All 18 tools appear to be READ_ONLY, but descriptions do not explicitly state this or explain recovery paths for common failures (e.g., 'wallet not found'). Tool names follow verb_noun convention (positive), but lack specificity, e.g., 'query-events' vs. 'search-events-by-type' is ambiguous. No evidence of parameter validation, pagination limits, or response field documentation.
Get count and details of active users
Check wallet status and loyalty information
Count total events with optional filtering
Get engagement trends over time
Evaluate a rule against sample events to test its logic
Retrieve list of wallets that own specific badges
Retrieve available event types in the system
Get rewards leaderboard rankings
Get referral statistics for a wallet
No input schemas visible in source code. Cannot verify parameter types, constraints, enums, or descriptions.
Tool descriptions are generic and under 50 characters. Lack LLM-optimized guidance on WHEN to use each tool, what it returns, and how it differs from similar tools (e.g., query-events vs. get-wallet-activity both retrieve data but serve different purposes).
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 38 | 2026-07-28+ | v2 |
Retrieve rewards and points information for a wallet
Get detailed information about a specific rule
Get list of top referrers by completed referrals
Get activity history for a wallet
List all loyalty rules with their configurations
Look up referral code details and usage
Get overall platform statistics and KPIs
Query loyalty events with filtering and pagination
Get comprehensive wallet summary with all loyalty data
No output schemas documented. LLMs cannot plan downstream tool calls or extract required fields (e.g., wallet_id, rule_id) for chaining. Baseline: 100% of A+ tools document return types.
No error handling patterns visible. No guidance on recovery (e.g., 'wallet not found, try check-wallet first'), error classification (retryable vs. user-fixable), or actionable error messages.
Tool definitions inferred from metadata only; actual src/tools/*.ts implementation not provided. Cannot verify pagination, limits, field naming consistency, or idempotency.