edu_video_gen
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SCENEXT_API_KEY | Yes | Your Scenext API key for authentication |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| gen_videoC | 生成教学讲解视频,生成时间大约需要10到20分钟，根据题目难度来定 Args: question: 问题内容（文本形式），question和questionImages中至少输入一个 answer: 参考答案（文本形式）：确保生成的讲解内容准确（可选） question_images: 问题内容（图片形式），输入图片的URL或者base64（可选） answer_images: 参考答案（图片形式），输入图片的URL或者base64（可选） quality: 视频质量，可选值：l(低)、m(中)、h(高)，默认为配置的默认质量 Returns: 包含任务ID的字典 |
| query_video_statusA |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have completely distinct purposes: gen_video creates educational videos, while query_video_status checks the status of those video generation tasks. There is no overlap in functionality, and an agent would never confuse one for the other.
Both tools follow a consistent verb_noun naming pattern: gen_video and query_video_status. The naming is clear, predictable, and uses the same snake_case convention throughout.
With only 2 tools, the server feels thin for a video generation service. While the core create+query workflow is covered, typical video generation domains might include additional operations like listing tasks, canceling tasks, or managing templates. The count is borderline but functional.
The server covers the essential create and query operations for video generation, forming a complete lifecycle. However, there are minor gaps: no tool to list or manage existing tasks, and no ability to cancel a task or adjust video parameters after submission. Agents can work around this, but it's not fully comprehensive.