Skip to main content
Glama
Fetchproof MCP Server

Fetchproof MCP Server

tiktok_search_keyword

Search TikTok videos by keyword phrase and retrieve paginated results from keyword pages for content research or trend analysis.

Instructions

tiktok: Search by Keyword (keyword pages). GET /v1/tiktok/search/keyword. Get TikTok videos for a phrase from TikTok's public keyword page for it (tiktok.com/discover/), 16 per page, as search_item_list of aweme_info objects (aweme_id, desc, create_time, author, statistics, video, music). The phrase is turned into the page's slug ("how to tie a tie" → how-to-tie-a-tie). Videos only: no accounts, hashtags or sounds. This covers only phrases TikTok has a keyword page for: most multi- Costs 1 credit when it succeeds. Errors, blocked or timed-out requests, invalid requests and cache hits cost nothing. A not-found or empty result is charged only where that operation's published cost says so.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "tiktok_search_keyword"
  }
}

Input Schema

NameRequiredDescriptionDefault
trimNoSet to true to get a trimmed response
queryYesThe phrase to look up, as words (how to tie a tie) or as the keyword page's slug (how-to-tie-a-tie)
cursorNoThe cursor string from the previous page's response ("<offset>:<session id>", such as 16:2026111707043796BD7F5020338800F556). It keeps later pages from repeating earlier ones; any other value returns 400
regionNoAccepted for compatibility but ignored: results are read as a US visitor
sort_byNoAccepted for compatibility but ignored: results keep the keyword page's order
date_postedNoAccepted for compatibility but ignored: keyword pages cannot be filtered by date

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: page size (16 per page), the response container (search_item_list of aweme_info with named fields), slug normalization of the query, video-only scope, coverage limits, and the exact credit/error/cache charging model. Gaps remain: no mention of auth requirements or rate limits, and the coverage caveat is truncated, so a key limitation is left unclear.

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

Conciseness4/5

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

Front-loaded with the action and source, then moves into response shape and cost, which is a sensible order. It is dense and largely waste-free, but the multi-sentence billing explanation is longer than needed for a search tool and the mid-sentence truncation ('most multi-') leaves a dangling, uninformative clause.

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?

With no output schema and no annotations, the description supplies the return structure, pagination model, scope limits and cost behavior, which is close to what an agent needs to invoke it correctly. Missing auth/rate-limit context and the broken coverage sentence keep it from being fully complete for a 6-parameter external-API tool.

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

Parameters3/5

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

Schema description coverage is 100%, so all six parameters are already documented in the schema, including the ignored region/sort_by/date_posted fields. The description adds only modest extra meaning, notably that the query phrase is normalized into the discover-page slug, which reinforces the schema's own example. That is a 3 baseline with a small lift, not a compensating explanation of parameter behavior.

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?

States a specific verb and resource ('Search by Keyword', 'Get TikTok videos for a phrase') plus the concrete upstream source (tiktok.com/discover/<phrase>) and the endpoint. It also draws the boundary against siblings by declaring 'Videos only: no accounts, hashtags or sounds', which lets an agent distinguish it from tiktok_search_hashtag or profile-oriented tools 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.

Usage Guidelines4/5

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

Gives clear when-to-use context (phrases that have a TikTok keyword/discover page) and a when-not signal ('This covers only phrases TikTok has a keyword page for'), plus cost conditions that inform whether to call it. It stops short of naming the alternative to use when hashtag or account results are wanted, and the coverage sentence is cut off mid-thought ('most multi-'), so the exclusion is incomplete.

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

Deploy Server

Other Tools