Skip to main content
Glama
TikTok Intelligence MCP Server

TikTok Intelligence MCP Server

by willowswt

search_tiktok_videos

Read-onlyIdempotent

Search TikTok videos by keyword or hashtag to retrieve video IDs, URLs, captions, engagement metrics, outlier multipliers, creator stats, and music metadata for trend and content research.

Instructions

Search TikTok videos by keyword or hashtag (keyword) and return video IDs, URLs, captions, views, likes, comments, shares, bookmarks, outlier multiplier (views/followers), creator stats, and music metadata.

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_tiktok_videos"
  }
}

Input Schema

NameRequiredDescriptionDefault
keywordYesTikTok search keyword or hashtag (e.g. "saas founder", "skincare").
maxResultsNoMaximum videos to return (1-20, default 8).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuine behavioral value by enumerating what comes back (metrics, outlier multiplier, creator stats, music metadata) in the absence of an output schema. It does not disclose coverage window, ordering, or rate/cost characteristics of the open-world search, which keeps it at a 3.

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?

A single front-loaded sentence with the action and scope first, and the long return-field enumeration is justified because no output schema exists. It is dense but every clause carries information; only the field list could be trimmed.

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?

For a two-parameter read-only search with rich annotations, the description covers purpose, input meaning, and the shape of results, which is what an agent needs to invoke it. Gaps around result ordering and search scope are minor but real.

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 both `keyword` and `maxResults` are already documented with examples and bounds. The description reinforces that `keyword` accepts a keyword or hashtag but adds no format or syntax detail beyond the schema, making the baseline 3 correct.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a precise verb+resource pairing ('Search TikTok videos by keyword or hashtag') and fixes the scope to keyword/hashtag lookup, which is enough to separate it from curation-style siblings like scan_breakout_tiktok_sounds. It stops short of explicitly naming which sibling to use instead in overlapping cases, so it is clear but not fully differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance and no mention of alternatives among the five sibling tools. The only usage signal is implicit in 'by keyword or hashtag', leaving the agent to infer that this is the general discovery entry point rather than a specialized scan.

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