Loading ToolBench
An MCP server that generates and transforms images using Google's Gemini model with image generation capabilities
Two tools with basic descriptions and partial schemas. Both tools have input schemas with type definitions and descriptions, meeting minimum requirements. However, descriptions are generic (avg 95 chars, below 194-char baseline) and lack actionable context for LLM selection. No output schemas documented. No error handling guidance. No parameter constraints (enums, ranges). Missing idempotency hints for WRITE operations. Tool names follow verb_noun pattern but descriptions don't explain WHEN to use each tool or what distinguishes them.
Generate an image based on the given text prompt using Google's Gemini model.
Transform an existing image based on the given text prompt using Google's Gemini model.
No output schema documented. LLMs cannot plan downstream operations or extract returned image paths/metadata.
Descriptions lack actionable context. Both tools describe WHAT they do but not WHEN to use them or how they differ. Descriptions should explain prerequisites (e.g., 'Requires GEMINI_API_KEY env var'), expected output format, and error recovery.
No error handling guidance. Code raises generic exceptions without telling LLM what to do next (retry, ask user, check API key). Missing recovery patterns.
WRITE operations lack idempotency hints or confirmation patterns. Agents may retry failed image generation calls, creating duplicate images. No dry-run or confirmation step.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 49 | <=2025-11-25 | v2 |
Base64 image parameter in transform_image_from_encoded lacks format validation. Description mentions required format but no regex pattern or enum constraint. LLMs may pass malformed data.