Loading ToolBench
MCP server that integrates Google Gemini AI for generating fictional weather alerts and forecasts
Server has 3 tools with significant definition gaps. gemini-prompt lacks any description (critical). gemini-alerts and gemini-forecast have descriptions but parameters lack descriptions in the first tool. All tools use Zod schemas (good), but descriptions are minimal and parameter documentation is incomplete. No error handling guidance, no output schema documentation, and no tool annotations. Naming is generic (verb_noun present but not action-oriented). This is a D-grade server with major issues.
Generate fictional weather alerts for a state using Gemini AI
Generate a fictional weather forecast for a location using Gemini AI
gemini-prompt has NO description. LLMs cannot determine when to select this tool without a description explaining its purpose and when to use it.
gemini-prompt parameter 'prompt' has null description. Parameter descriptions are mandatory for LLM reasoning. The description field is explicitly null in the schema.
No output schema documentation. Tools return text content but LLMs have no formal schema describing the response structure, fields, or types.
No error handling guidance. Catch blocks return generic failure messages without actionable recovery steps. LLMs cannot determine if errors are retryable or what to do next.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 41 | 2026-07-28+ | v2 |
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). All tools are marked READ_ONLY but this is not declared in the tool definitions themselves.