Loading ToolBench
MCP server with OAuth 2.0 authorization provider running on Cloudflare Workers, demonstrating remote authentication flows
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 (null). Output schema is inferred from code (returns text content) but not documented. No error handling guidance. Naming is acceptable (verb_noun pattern) but insufficient to overcome missing descriptions and documentation.
Tool 'add' has no description. LLMs cannot determine when or why to select this tool without a description explaining its purpose, when to use it, and what it returns.
All input parameters (a, b) lack descriptions. Parameter descriptions are null. LLMs cannot infer that 'a' and 'b' are operands for addition, they need explicit descriptions like 'First number to add' and 'Second number to add'.
Output schema is not documented. The tool returns text content but there is no schema documentation explaining the response structure. LLMs need to know what fields to expect.
No error handling or recovery guidance. If the tool fails (e.g., invalid input types), there is no error message telling the LLM what to do next or how to self-correct.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 36 | 2026-07-28+ | v2 |
Tool naming 'add' lacks verb clarity. While 'add' is a verb, it is ambiguous in isolation, does it add numbers, items to a list, or users to a group? A more specific name like 'add_numbers' or 'calculate_sum' would be clearer.