Skip to main content
Glama
Crawlora MCP

Crawlora MCP

Official

tiktok_mobile_live_room_by_user

Retrieve the TikTok LIVE room a specific user is currently streaming by user_id, returning room status, viewer counts, owner stats, and stream URLs.

Instructions

LIVE room by user: the room a user is currently streaming. Returns the LIVE room a TikTok user is currently streaming, keyed by user_id. The upstream is /webcast/room/info_by_user/ on the webcast edge host (no origin header) and returns the same room payload as /api/v1/tiktok/mobile/live/room (title, status, concurrent viewers, owner, cumulative stats, per-resolution FLV URLs, cover and the ~500-key room object in data), except that the caller addresses a user and the room id is filled from the payload (both user_id and room_id are echoed). Measured 2026-10-22: user_id=6707748031095751686 answered 184,575 B (195,220 B on the second webcast host); anchor_id alone answers a 57-byte empty payload, so user_id is the address. A user with no live room answers status 30003 "room has finished" and is surfaced as a 400; a non-numeric user id is a 400 (status 10011); a bare call answers a 57-byte empty success envelope, which is why this endpoint requires user_id.

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": {
      "user_id": "<user_id>"
    },
    "name": "tiktok_mobile_live_room_by_user"
  }
}

Input Schema

NameRequiredDescriptionDefault
user_idYesNumeric TikTok user id (e.g. the owner id from a profile, video author or live search row)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.16

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses the upstream host and path, payload size observations, that a user with no live room surfaces status 30003 as a 400, that a non-numeric id is a 400 (10011), and that both `user_id` and `room_id` are echoed. That is exactly the error/permission profile an agent needs and cannot get from structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

The core sentence is front-loaded and the response/error details earn their place, but the measured byte counts from a specific date and the comparison of two webcast hosts are debugging trivia that pad a one-parameter tool description. It is longer than an agent selecting a tool needs.

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?

For a single-required-parameter read tool with no output schema, nothing important is missing: the description enumerates the returned fields (title, status, concurrent viewers, owner, stats, FLV URLs, cover, ~500-key room object) and covers the failure modes, so an agent knows what it will get and when it will error.

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 already 100%, so the baseline is 3; the description goes further by explaining the parameter must be numeric, that the id can come from a profile/video author/live search row, and that the analogous `anchor_id` does not work as an address. It adds real meaning rather than restating the schema.

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 specific verb+resource: 'the room a user is currently streaming', keyed by `user_id`. It explicitly contrasts itself against the sibling live-room endpoint, noting it returns the same payload as `/api/v1/tiktok/mobile/live/room` except the caller addresses a user and the room id is filled from the payload, so an agent can pick between the two 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?

It establishes the precondition clearly: `user_id` is the address, `anchor_id` alone yields a 57-byte empty payload, and a bare call returns an empty success envelope — effectively 'use this only when you have a numeric user id'. It does not name the sibling tools (e.g. tiktok_mobile_live_room) as alternatives by name, so routing guidance is strong but not fully 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