Skip to main content
Glama

generate_note

Submit a video link or local file to generate AI Markdown notes asynchronously. Configure platform, style, quality, and optional screenshots or summaries.

Instructions

提交一个视频链接/本地文件,异步生成 AI Markdown 笔记。

- video_url: 必填,B 站/YouTube/抖音/快手链接或本地文件路径;
- platform: 可省略,自动识别;
- quality: fast / medium / slow;
- provider_id: LLM 供应商 id(先 list_providers 查看,add_provider 新增);
- model_name: 省略时取已配置的默认模型(setup 向导设置),否则取该供应商第一个可用模型;
- format: 附加内容,如 ["toc","link","screenshot","summary"];
- style: 输出风格(minimal 精简/detailed 详细/academic 学术/tutorial 教程/xiaohongshu 小红书/life_journal 生活向/task_oriented 任务导向/business 商业风格/meeting_minutes 会议纪要);
- extras: 附加到 prompt 末尾的自定义指令(如自定义笔记风格要求);内置风格用 style,自定义风格用 extras;
- video_understanding / video_interval / grid_size: 视频理解(需多模态模型);不传时用 setup ③ 配置的默认(默认关 / 6s);显式传入始终覆盖;
- screenshot + format 含 "screenshot": 插入图片,产出便携笔记 note.md + Assets/(相对引用);
- notes_dir: 便携笔记的输出目录(可选;缺省 BILINOTE_NOTES_DIR 环境变量,再缺省 note_results/{task_id}/)。

返回 {task_id, status, platform}。之后用 get_task_status / wait_for_note 查询结果;
SUCCESS 时 result.note_dir 指向便携笔记目录。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
linkNo
styleNo
extrasNo
formatNo
qualityNomedium
platformNo
grid_sizeNo
notes_dirNo
video_urlYes
model_nameNo
screenshotNo
provider_idNo
video_intervalNo
video_understandingNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does so effectively. It discloses async behavior, return struct, polling requirement, default overrides, output directory conventions, and screenshot behavior. This is thorough.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Structured bullet list, front-loaded with main purpose. Each parameter gets a concise explanation without fluff. The length is justified by the 14-parameter complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all key invocation details including return values and follow-up tools. However, the undocumented 'link' parameter and lack of failure-behavior details slightly reduce completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Description explains all parameters except the 'link' boolean, which is absent. It adds context for platform auto-detection, quality options, model selection, format list, style categories, and custom extras. The missing param is a minor gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states '提交一个视频链接/本地文件,异步生成 AI Markdown 笔记' which specifies the action (generate), input (video URL/local file), and async nature. It clearly differentiates from sibling result-retrieval tools like get_task_status and wait_for_note.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly instructs to use list_providers/add_provider for provider_id and get_task_status/wait_for_note for results. It also notes defaults from setup and fallback for notes_dir, providing actionable guidance for invocation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/HuangYincan/BiliNote-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server