Loading ToolBench
A Model Context Protocol (MCP) server implementation for Cloudflare's Flux 1 Schnell AI image generation model
Single tool with minimal definition quality. Tool name 'text-to-image' lacks action verb prefix (should be 'generate_image'). Description is adequate (47 chars) but generic. No output schema documented. No error handling guidance. No pagination, no result limits, no chaining IDs. Fails multiple baseline checks: 100% of A+ tools have param descriptions (this has zero); 100% of A+ tools document return types (this does not).
Generate an image from a text prompt
Tool name lacks action verb. 'text-to-image' should be 'generate_image' to signal intent clearly to LLMs.
Input parameters lack descriptions. 'prompt' and 'steps' have no descriptions in the schema, LLMs cannot infer meaning or constraints. Rubric baseline: 100% of A+ tools have param descriptions.
Output schema not documented. Tool returns image data but no schema is declared for the response structure. LLMs cannot plan downstream operations or validate results.
No error handling guidance. Tool calls external Cloudflare API but provides no recovery hints if the API fails, times out, or returns invalid data. LLM has no guidance on retry strategy.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 39 | 2026-07-28+ | v2 |
API credentials exposed via environment variables without validation. No check that CLOUDFLARE_ACCOUNT_ID and CLOUDFLARE_API_TOKEN are set before tool invocation, will fail at runtime with unhelpful error.