Skip to main content
Glama
Crawlora MCP

Crawlora MCP

Official

tiktok_mobile_search_effects

Search TikTok effects and stickers by keyword to find matching effects; use the returned cursor and search_id together to retrieve additional results.

Instructions

Search TikTok effects/stickers by keyword. Searches TikTok's effect catalogue by keyword, returning the app's full effect objects (name, hint, icon_url, file_url, effect_id, types, tags, parent/children, effect_type, music, source, designer_id, schema). The upstream is /aweme/v1/search/effect/; the page is unfolded to the top level (effects, cursor, has_more, search_id, use_hot, plus bind_effects/collection on some queries). Paging is real but needs BOTH halves of the token: pass the previous response's cursor and search_id together (measured: page 1 cursor: 100, page 2 with cursor=100&search_id=... returned the final effect with has_more: false; a cursor without its search_id returns an empty page, which the service rejects as a 400). count and offset were measured as no-ops. Measured 2026-10-21: keyword=green screen -> 6 effects (11,831 B) + 1 on page 2, green -> 2, 字幕 -> 4; a keyword with no matches is a valid empty page.

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": "tiktok_mobile_search_effects"
  }
}

Input Schema

NameRequiredDescriptionDefault
countNoAccepted for shape parity; the server was measured to ignore it
cursorNoNext-page token from the previous response (0 = first page)
keywordYesEffect name or text, e.g. green screen
search_idNoSearch-session token from the previous response; required together with cursor

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.16

TDQS

A4.3/5.0
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 it well: it discloses the upstream endpoint, the flattened page shape, the two-part paging token with a measured failure mode (cursor without search_id returns an empty page, rejected as 400), and that count/offset are measured no-ops. It would only earn a 5 by also mentioning auth or rate-limit behavior, which it omits.

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?

Front-loaded with purpose, then return shape, then paging mechanics, then measured evidence. Every sentence carries non-redundant operational information, and the return-field enumeration earns its length because there is no output schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A 4-parameter search tool with no annotations and no output schema still leaves nothing critical unexplained: return fields are enumerated, the paging token contract is spelled out, dead parameters are flagged, error behavior is described, and the empty-result case is normalized.

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 coverage is 100% and the schema already documents each of the four parameters, including that count is ignored and that search_id is required with cursor, so the description mostly restates structured data. The added value is the concrete worked example (page 1 cursor: 100, page 2 with cursor=100&search_id=... ends at has_more: false) and the 400 consequence, which lifts it modestly above baseline.

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 TikTok effects/stickers by keyword') and names the exact data source ('TikTok's effect catalogue'). The keyword-search framing plus the enumerated effect fields cleanly separates it from the sibling browse tools (tiktok_mobile_trending_effects, tiktok_mobile_live_effects) and from the sibling keyword searches for music/hashtags/users/places.

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 operational conditions: supply a keyword, page only by passing the previous response's cursor together with search_id, and expect a valid empty page for non-matching keywords. It never names an alternative tool or states when-not-to-use, so the sibling routing is left implicit rather than explicit.

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