按关键词搜索好看视频，返回视频摘要并支持分页；用于查找视频，不用于读取指定视频链接的详情或查找用户。
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | 视频搜索词，例如科技、美食或品牌名；不要传视频链接、用户主页链接或分页令牌。 | |
| page_token | No | 分页令牌，首次请求留空；继续翻页时将上一页完整 next_page_token 原样传回，不得修改、截断或自行生成；只能用于相同工具和相同关键词。 |
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes | 当前页视频搜索结果，按搜索结果顺序返回。 | |
| points | Yes | 本次成功调用的积分消耗与账户积分余额。 | |
| next_page_token | Yes | 下一页不透明分页令牌；为空表示没有下一页。继续翻页时原样作为 page_token 传回，只能用于相同工具和相同关键词。 |
Changes observed during successful MCP inspections.
Output schema / properties / points / descriptionPrevious value: -"本次成功调用的积分消耗与调用完成时的账户积分余额。"New value: +"本次成功调用的积分消耗与账户积分余额。"Output schema / properties / points / properties / balance / descriptionPrevious value: -"本次接口完成时看到的当前积分余额，可为负数。"New value: +"优先返回调用完成时查询到的账户积分余额。查询失败时，回退到本次预扣后的余额快照。余额可为负数。"Output schema / properties / points / properties / balance / descriptionPrevious value: -"本次接口完成时看到的当前积分余额。"New value: +"本次接口完成时看到的当前积分余额，可为负数。"Output schema / properties / points / properties / balance / minimumRemoved value: -0Output schema / properties / items / items / properties / author / properties / name / titleAdded value: +"Name"Output schema / properties / items / items / properties / author / properties / user_id / titleAdded value: +"User Id"Output schema / properties / items / items / properties / author / titleAdded value: +"HaokanVideoAuthor"Output schema / properties / items / items / properties / cover_image_url / titleAdded value: +"Cover Image Url"Output schema / properties / items / items / properties / duration_seconds / titleAdded value: +"Duration Seconds"Output schema / properties / items / items / properties / publish_time_text / titleAdded value: +"Publish Time Text"Output schema / properties / items / items / properties / share_url / titleAdded value: +"Share Url"Output schema / properties / items / items / properties / title / titleAdded value: +"Title"Output schema / properties / items / items / properties / video_id / titleAdded value: +"Video Id"Output schema / properties / items / items / properties / view_count / titleAdded value: +"View Count"Output schema / properties / items / items / properties / view_count_text / titleAdded value: +"View Count Text"Output schema / properties / items / items / titleAdded value: +"HaokanSearchVideoItem"Output schema / properties / items / titleAdded value: +"Items"Output schema / properties / next_page_token / titleAdded value: +"Next Page Token"Output schema / titleAdded value: +"HaokanVideoSearchResult"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds value beyond them by saying results are video summaries and that paging is supported, which tells the agent this is a discovery surface rather than a detail fetch. It doesn't mention result volume or ordering, but the output schema covers return shape.
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?
Two compact clauses with the capability stated first and the exclusions second; almost no waste. The semicolon-joined density is slightly terse but remains readable and front-loaded.
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 two-parameter read-only search tool with full schema coverage, annotations, and an output schema, the description covers what it does, what it returns, and what it is not for. No critical gap remains for correct invocation.
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 100%, and the schema already explains both keyword and page_token in detail, including that tokens must be passed back unmodified for the same keyword. The description only implies keyword search and pagination, adding essentially nothing beyond the structured fields, so the baseline 3 applies.
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?
States a specific verb and resource ('按关键词搜索好看视频'), plus what it returns ('视频摘要') and that it supports pagination. The second clause explicitly excludes video-detail-by-URL and user lookup, which separates it from haokan_get_video_detail_by_url and haokan_search_users.
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?
Gives a clear positive condition ('用于查找视频') and explicit exclusions (reading detail of a specific video URL, finding users), which routes the agent to the right sibling family. It stops short of naming the exact alternative tools, so an agent still has to map 'find users' to haokan_search_users itself.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.