获取 TikTok 搜索框联想词，不返回作品或用户详情，不支持分页；可将 text 用于作品搜索，已有明确搜索词时可直接搜索作品；已有作品或用户主页链接时使用对应详情工具。
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | 非空搜索关键词或短语，例如 camping、美食；不要传视频链接、用户链接、ID 或分页令牌。 |
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes | 搜索建议列表，保持返回顺序；没有匹配建议时为空数组。 | |
| points | Yes | 本次成功调用的积分消耗与账户积分余额。 |
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 / text / titleAdded value: +"Text"Output schema / properties / items / items / titleAdded value: +"TikTokSearchSuggestionItem"Output schema / properties / items / titleAdded value: +"Items"Output schema / titleAdded value: +"TikTokSearchSuggestionsResult"Input schema / properties / keyword / descriptionPrevious value: -"搜索关键词或短语，例如 camping、美食；不要传视频链接、用户链接、ID 或分页令牌。"New value: +"非空搜索关键词或短语，例如 camping、美食；不要传视频链接、用户链接、ID 或分页令牌。"Input schema / properties / keyword / patternAdded value: +".*\\S.*"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the supplied readOnlyHint/openWorldHint, it discloses two things annotations cannot: no pagination support and that results contain suggestions only, not post or user records. It does not mention rate limits or how long the response is, which keeps it short of a 5.
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?
One dense, semicolon-delimited sentence that front-loads what is returned before covering exclusions and alternatives. Every clause carries routing information; the only cost is slightly compressed phrasing that reads as a list rather than prose.
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 one-parameter read tool with a full schema, complete parameter documentation, and an output schema that removes any need to describe return shape, the description covers scope, non-pagination, and sibling routing. Nothing essential for a correct call is missing.
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 keyword description already spells out the non-empty pattern and forbids links/IDs/tokens, so the description adds no further meaning for the single parameter. The reference to 'text' describes the output, not the input, so it does not raise the bar here.
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: 获取 TikTok 搜索框联想词 (get TikTok search-box suggestions). It immediately bounds the output ('不返回作品或用户详情') and separates itself from the search/detail siblings, so an agent can pick it without opening the schema.
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 explicit routing rules: use the returned text for post search, skip straight to post search when a clear query already exists, and use the detail tools when a post or profile URL is already in hand. All three alternatives are named with the condition that selects them.
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.