Loading ToolBench
A remote MCP server with OAuth 2.0 authentication provider running on Cloudflare Workers
Single tool 'add' has critical definition gaps. Input schema present with Zod types (a, b as numbers) but parameter descriptions are null, violating the requirement that every parameter needs a description. Tool description is missing entirely (no docstring visible in registration). Output schema is inferred from response structure but not formally documented. No error handling guidance. Naming is acceptable but lacks context about when/why to use this tool. This server appears to be a minimal demo rather than production-grade.
Tool 'add' has no description. LLMs cannot determine when or why to select this tool without a docstring explaining its purpose, inputs, and outputs.
All input parameters (a, b) lack descriptions. Parameter descriptions are null in the schema. LLMs cannot infer that 'a' and 'b' are operands for addition without explicit text.
Output schema is not formally documented. Response structure is inferred from code (text content array) but not declared in tool metadata. LLMs need explicit output schema to plan downstream calls.
No error handling or recovery guidance. Tool provides no error messages, validation, or hints for invalid inputs (e.g., non-numeric values).
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 32 | 2026-07-28+ | v2 |
Tool name 'add' is generic and lacks context. Does not follow verb_noun convention (e.g., 'calculate_sum' or 'add_numbers' would be clearer). Ambiguous for LLM selection in a larger toolkit.