iOS application for managing MCP tool pricing models, constraints, and operator credentials. Provides UI for pricing configuration, constraint chain editing, and batch operations on tools.
Critical gaps across all dimensions. Tool definitions exist in ToolRole.swift but lack visible input/output schemas, parameter descriptions, and detailed docstrings. No evidence of JSON Schema definitions, parameter type constraints, or error handling guidance. Descriptions are minimal (10-30 chars) and do not explain WHEN to use each tool or WHAT it returns. No pagination, no output field documentation, no recovery guidance for errors. Transport mechanism unknown (likely STDIO given Swift/iOS context). This server is not production-ready for agent integration.
Get account statement (patron or operator perspective)
Get account statement as infographic (patron or operator perspective)
Certify credits for operator identity
Check patron account balance
Check payment status for patron
Forget stored credentials for patron
Get pricing model for a tool (patron or operator perspective)
No input schemas visible in source code. All 16 tools lack JSON Schema definitions for parameters, types, constraints, and descriptions. Cannot verify parameter validation or LLM-friendly input guidance.
Descriptions are minimal (10-30 characters) and lack context. No explanation of WHEN to use each tool, WHAT it returns, or HOW it differs from similar tools. LLMs cannot reliably select the correct tool.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 33 | 2025-06-18+ | v2 |
Check operator identity status
Purchase credits for patron identity
Receive credentials for patron identity
Register a new operator identity
Request credential channel for patron
Restore credits for patron identity
Check service status for patron
Check patron session status
Set pricing model for a tool (operator identity required)
No output schemas documented. Unclear what fields each tool returns, their types, and what data is available for downstream tool chaining. Agents cannot plan multi-step workflows.
No error handling guidance. Unclear which errors are retryable, which require user intervention, and what recovery steps are available. Agents will fail silently or retry indefinitely.
Destructive operations (certify_credits, purchase_credits, restore_credits, forget_credentials, receive_credentials) lack confirmation or dry-run support. Agents may execute irreversible actions without safeguards.