Skip to main content
Glama
Sign In
Crawlora MCP

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

tiktok_mobile_search

Search TikTok videos by keyword through the mobile API and return unmodified result documents with video stats, profile and pagination metadata for building feeds, monitoring, or research.

Instructions

Search TikTok videos on the mobile API. Keyword search returning the mobile API result documents unmodified: each entry has aweme_info (a full video object with statistics), card_profile and search metadata, plus cursor and has_more. Keep count small (20 already exceeds one megabyte of upstream JSON).

Input Schema

NameRequiredDescriptionDefault
countNoResults per page (max 20)
offsetNoResult offset; pass search_id with a non-zero offset
keywordYesSearch keyword
search_idNosearch_id returned by a previous page of the same search

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.17.16
    • changedInput schema / properties / offset / description
      Previous value: -"Result offset"New value: +"Result offset; pass search_id with a non-zero offset"
    • addedInput schema / properties / search_id
      Added value: +{
+  "description": "search_id returned by a previous page of the same search",
+  "type": "string"
+}
  2. Addedv1.17.13

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses that upstream documents are returned unmodified, names the top-level fields (aweme_info, card_profile, cursor, has_more), and warns that count=20 already exceeds ~1MB of JSON. Auth requirements and rate limits are still unstated, 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.

Conciseness5/5

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

Three sentences, each doing distinct work: what it searches, what comes back, and the one operational caveat. The payload warning sits at the end where it will be read before the call.

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?

No output schema exists, and the description compensates by describing the return envelope and pagination fields. For a 4-parameter search tool it is nearly complete; only caller-side concerns like auth or locale/region scoping are missing.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3; the description goes beyond it by explaining why count should stay small (payload size) and by anchoring count to real output volume. It does not add anything about offset/search_id pairing beyond what the schema already says.

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?

States a specific verb and resource ('Search TikTok videos on the mobile API. Keyword search') and implies a general keyword feed rather than user/hashtag/effect search. It never names siblings such as tiktok_mobile_search_user or tiktok_search, so differentiation is left implicit.

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

Usage Guidelines3/5

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

'Keyword search' implies the use case (query-driven video discovery) but there is no explicit when-to-use versus tiktok_search or the other tiktok_mobile_search_* endpoints, and no exclusions or prerequisites stated.

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