Loading ToolBench
MCP server with OAuth 2.0 authorization provider running on Cloudflare Workers, demonstrating remote authentication flows
Single tool 'add' has a clear, concise description (27 chars) and properly typed input schema with parameter descriptions. However, the tool lacks output schema documentation, which is critical for LLM planning. The description is minimal but adequate. No error handling guidance, no idempotency hints, and no indication of side effects. The tool is trivial (arithmetic), but production tools need richer metadata. Naming is acceptable but generic, 'add' lacks the verb_noun pattern (e.g., 'add_numbers' would be clearer in a multi-tool context).
Adds two numbers together
Output schema not documented. LLMs cannot plan downstream calls or extract results without knowing the response structure.
Tool description is too brief (27 chars). Should explain WHAT it does, WHEN to use it, and what it returns (target 50-200 chars).
No error handling guidance. If inputs are invalid (NaN, Infinity, null), the tool should return actionable error messages, not stack traces.
Tool name 'add' is generic. In a multi-tool context, 'add_numbers' or 'calculate_sum' would be clearer and follow verb_noun convention.
No tool annotations (readOnlyHint, idempotentHint). The 'add' tool is read-only and idempotent, these hints help agents reason about safety and retry logic.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 50 | 2026-07-28+ | v2 |