Loading ToolBench
MCP integration for Arda API - provides read-only access to authentication, user profiles, company information, deals, and market metrics
Critical failures across all 9 tools. ZERO input schemas visible in source code, all tools show 'Input: {}' with no parameter definitions. Descriptions are present but generic (10-50 chars), lacking WHEN/WHY guidance. No output schemas documented. Tools 1-3 are meta-discovery (list_resources, list_prompts, list_tools) with trivial descriptions. Tools 4-9 are API wrappers (verify_user_identity, get_company_full_context, etc.) with empty input specs, making them unusable by LLMs without guessing required parameters. No error handling guidance. No parameter constraints, enums, or validation rules visible. This server exposes raw OpenAPI specs via FastMCPOpenAPI but provides no MCP-layer schema refinement.
Perform detailed analysis of a specific deal.
Troubleshoot authentication and access issues.
Retrieve complete company information including KYB, team, and financial details.
List all contextual workflow prompts. Returns a list of prompt names. Prompts provide contextual guidance on WHEN and WHY to use specific API operations.
List all MCP resources and resource templates. Resources are static endpoints. Templates require path parameters like {user_id}.
List all MCP tools (functions you can call). Returns a list of tool names. Tools include both API operations and meta-tools like this one.
ALL 9 tools have empty input schemas ('Input: {}') with zero parameter definitions. LLMs cannot determine what parameters are required, optional, or their types/constraints. This violates the fundamental requirement that every parameter must have a description and type.
No output schemas documented for any tool. LLMs cannot plan downstream calls or extract required fields (e.g., user_id, company_id) needed for chaining. Violates pattern:tool and pattern:response-shaper.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 35 | 2026-07-28+ | v2 |
Analyze market trends and deal distribution patterns.
Get comprehensive financial overview for a user.
Verify authenticated user identity and determine their access permissions.
Descriptions are too short (10-50 chars) and lack WHEN/WHY context. E.g., 'Verify authenticated user identity and determine their access permissions' (67 chars) does not explain when to call it vs other tools, what prerequisites exist, or what the response contains. Baseline for A+ tools is 50-200 chars with explicit guidance.
No error handling guidance. Tools do not document what errors are retryable, user-fixable, or fatal. No recovery hints (e.g., 'If authentication fails, call authentication_troubleshooting first'). Violates pattern:recovery-guide.
Tool names for API wrappers (tools 4-9) are vague and do not clearly distinguish between similar operations. E.g., 'get_company_full_context' vs 'analyze_deal_details', unclear what 'full_context' includes or how it differs from other company tools. Naming should follow verb_noun pattern with clear disambiguation.