Skip to main content
Glama

Search TT Videos

search_tt_videos
Read-onlyIdempotent

[read] Find TikTok videos and image posts for a keyword (source SEARCH: keyword search, HASHTAG: the posts of the hashtag the keyword names). Each video has aweme_id, title, user_id and video_url (a signed, short-lived mp4 address, null for image posts: pass it to add_storage_remote_files at once to keep the file); users lists those authors (user_id, username, nickname); region (two letters) and language filter the result. Pass the aweme_ids you want studied to analyze_tt_trend_media. The first page is one priced search.

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": {
      "keyword": "<keyword>"
    },
    "name": "search_tt_videos"
  }
}

Input Schema

NameRequiredDescriptionDefault
countNo
offsetNo
regionNo
sourceNoHASHTAG
keywordYes
languageNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only declare read-only/open-world/idempotent; the description goes well beyond that by disclosing that `video_url` is a signed, short-lived mp4 (null for image posts), that it must be forwarded to add_storage_remote_files immediately to persist the file, and that 'the first page is one priced search' — a cost signal an agent needs before calling.

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 purpose and the mode switch, then the return shape, then the next-step routing. It is dense but every clause carries information; the semicolon-chained sentences make it slightly harder to scan than it could be.

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, the description usefully enumerates the returned fields (`aweme_id`, `title`, `user_id`, `video_url`, `users`, `region`, `language`) and flags the ephemeral URL hazard. The remaining gap is pagination — count/offset behavior is left entirely unexplained.

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 0%, so the description carries the burden; it does explain `source` values, `region` format (two letters) and `language` filtering, plus the `aweme_id`/`users` returns. But `count` and `offset` — the pagination controls — are never mentioned, leaving two of six parameters undocumented anywhere.

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 — 'Find TikTok videos and image posts for a keyword' — and immediately sub-divides into the two lookup modes via `source`. An agent can tell this apart from list_tt_videos or search_ig_trends without opening any 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 real routing guidance: explains the SEARCH vs HASHTAG choice, and explicitly says to pass the returned `aweme_id`s to analyze_tt_trend_media for study. It does not say when to prefer this over the sibling list_tt_videos, so it stops short of full when/when-not coverage.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.