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. Input schema present with Zod types (a, b as numbers) but parameter descriptions are null, violates the requirement that every parameter needs a description. Tool description is missing entirely (no docstring visible in registration). Output schema not documented. No error handling guidance. Naming is generic and doesn't follow verb_noun pattern (should be 'sum_numbers' or 'calculate_sum'). This server fails multiple hard scoring rules: missing tool description (→ description score 0), null parameter descriptions (→ schema score capped at 30), and no documented output schema.
Tool 'add' has no description. LLMs cannot determine when or why to select this tool without a docstring explaining its purpose, when to use it, and what it returns.
All input parameters (a, b) have null descriptions. Parameter descriptions are mandatory, LLMs cannot infer that 'a' and 'b' are operands for addition without explicit text.
Output schema is not documented. The tool returns {content: [{type: 'text', text: string}]} but this structure is not declared in the tool definition, forcing LLMs to guess the response format.
Tool name 'add' is generic and does not follow verb_noun convention. Should be 'sum_numbers' or 'calculate_sum' to clearly signal the action and operands.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 26 | 2026-07-28+ | v2 |
No error handling or recovery guidance. If inputs are invalid (non-numeric), the tool provides no actionable error message to guide the LLM to retry or correct the call.