Loading ToolBench
MCP server with OAuth 2.0 authentication provider for remote authorization, built on Cloudflare Workers
Single tool 'add' has critical definition gaps. Input schema present but parameters lack descriptions (null values). Tool description missing entirely. No output schema documented. Naming is generic and does not follow verb_noun pattern. This server fails baseline quality checks for production use.
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.
Input parameters 'a' and 'b' have null descriptions. Every parameter must have a non-empty description explaining what it controls. LLMs cannot infer that these are operands for addition.
Tool name 'add' is generic and does not follow verb_noun pattern. Should be 'calculate_sum' or 'add_numbers' to clarify intent. Current name is ambiguous, does it add to a list, add a user, or perform arithmetic?
No output schema documented. The response structure (content array with text field) is inferred from code but not declared in tool metadata. LLMs need explicit output schema to plan downstream calls.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 26 | 2026-07-28+ | v2 |
Tool performs arithmetic but returns result as string ('String(a + b + 1)'). Logic error: adds 1 to the sum unexpectedly. Behavior is undocumented and likely unintended.