Loading ToolBench
An MCP server deployed on Cloudflare Workers with OAuth 2.0 authentication support, demonstrating remote MCP server capabilities with a simple arithmetic tool
Single tool 'add' has critical definition gaps. Tool description is missing entirely (null in source). No output schema documented. No error handling guidance. Naming is generic ('add') without context about what domain this serves. This server appears to be a minimal demo/template rather than production-grade tooling.
Tool 'add' has no description. LLMs cannot determine when or why to select this tool without a description explaining its purpose, domain, and when to use it.
Parameters 'a' and 'b' have null descriptions. Every parameter must have a non-empty description explaining what it controls. 'a' and 'b' are ambiguous, are these operands? Coefficients? Identifiers?
No output schema documented. The tool returns {content: [{type: 'text', text: string}]} but this structure is not declared in the tool definition. LLMs cannot plan downstream calls without knowing the response shape.
Tool name 'add' is generic and lacks domain context. Is this arithmetic addition? Data aggregation? Without a description, the LLM cannot disambiguate. Consider 'calculate_sum' or 'add_numbers' with a clear description.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 33 | 2026-07-28+ | v2 |
No error handling guidance. What happens if 'a' or 'b' is null, undefined, or non-numeric? No recovery hints provided to the LLM.