Search Kuaishou videos by keyword, filter by sorting, and view title, author, play, like, comment, and favorite counts. Open direct links for details or extract video info and captions.
快手作品搜索工具。输入关键词就能搜到快手热门作品（广域库），支持按排序方式多维度筛选，作品标题、作者、播放数、点赞数、评论数、收藏数一览无余，点一下链接就能跳转看详情，还可提取视频详情和文案。当用户需要搜索快手作品、查找快手热门内容、查询快手作品数据时使用。触发词：快手搜索、快手作品、快手热门、快手视频查询、搜快手。
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | page | |
| size | No | size | |
| sort | No | sort | |
| keyword | Yes | keyword |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.4Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry behavioral disclosure. It does disclose key behavior: searching returns work stats, links open details, and it can extract video details and copy. However, it does not mention output format, pagination behavior, rate limits, or whether any authentication or permissions are required, which leaves some transparency gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is efficient and front-loaded with the primary purpose, followed by output fields and usage triggers. The trigger-word list is somewhat redundant with the usage sentence, but overall every sentence contributes useful orientation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 4-parameter tool with no output schema and no annotations, the description covers purpose, result fields, and usage context. However, it omits the accepted sort values and the meaning/effect of page and size, which are required for an agent to invoke it correctly with multi-dimensional filtering.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is reported at 100% but the property descriptions are mere labels ('keyword', 'page', 'size', 'sort') with no real meaning. The description adds semantics for keyword ('输入关键词') and partially for sort ('按排序方式多维度筛选'), but page and size remain unexplained. This fits the baseline of 3 for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: searching Kuaishou works, specifically '热门作品（广域库）'. It enumerates the returned fields (title, author, play count, likes, comments, favorites) and the ability to jump to details and extract video content. This clearly separates it from sibling tools like kuaishou-account-works or kuaishou-comment.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to use it: when the user needs to search Kuaishou works, find hot content, or query work data, and even lists trigger words. It lacks an explicit when-not-to-use or named alternatives, but the use case is clear enough to route an agent correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.