Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

tiktok_mobile_user_recommendations

Find TikTok mobile Following-page creator recommendations, returning full profiles and up to three recent videos per suggested account.

Instructions

Recommended creators on the mobile app's Following page. Returns the app's suggested creators for the Following page unmodified: user_list entries are {user, aweme_list} where user is the full creator projection (uid, sec_uid, nickname, signature, avatars, follower/following counts, verification and privacy flags) and aweme_list holds up to three recent videos, so this is a creator-discovery surface rather than a bare id list. The route has no paging fields and returns one page of 13-17 creators (fresh recommendations differ per call). count is accepted for parity but the gateway was measured to ignore it. The route is not signature-value gated, so unlike the profile/posts routes it does not need the device-backed signer.

Input Schema

NameRequiredDescriptionDefault
countNoRequested page size; forwarded when set, but the gateway was measured to ignore it

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.16

TDQS

A4.2/5.0
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: it discloses the one-page, non-paged route, a variable page size of 13-17, per-call freshness of results, that count is silently ignored, and that the route is not signature-value gated so no device-backed signer is needed. Missing only operational details such as rate limits or whether results depend on the caller's logged-in account.

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?

Three sentences, front-loaded with the resource and its distinction from an id list, then the response shape, then the practical caveats. The inline enumeration of projection fields is dense but earns its place by removing the need for an 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?

No output schema and no annotations exist, yet the description supplies the response envelope, the per-entry structure, the page size range, and the auth/signing status. Nothing an agent needs in order to call this correctly and interpret the result is missing.

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 single param already documents that count is forwarded but ignored by the gateway. The description restates the same fact rather than adding new semantics, so the baseline 3 for fully-documented parameters applies.

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?

Opens with a concrete verb+resource: suggested creators for the mobile app's Following page, and immediately distinguishes the surface from 'a bare id list' by describing user_list entries as full creator projections plus up to three recent videos. An agent can tell exactly what it gets without opening a 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?

Frames the tool as a 'creator-discovery surface' and rules out paging-based usage, which steers an agent to call it once rather than paginate. It stops short of naming a sibling alternative (e.g. tiktok_mobile_search_user for targeted creator lookup) or stating when not to use it.

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