Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

tiktok_mobile_place_videos

Fetch a page of TikTok videos posted at a specific place using its poi_id, with cursor-based pagination for retrieving subsequent pages.

Instructions

Videos posted at one place (paged). Returns one page of the videos posted at a place, keyed by the poi_id that the place search endpoint returns. The upstream is /tiktok/poi/video/list/v1: aweme_list holds the app's full video objects (id, description, author, statistics, media URLs, music, anchors, ...) and item_count is this page's size. Page with cursor: the returned cursor is a reusable next-page token (measured page 1 cursor: 20 with has_more: 1, page 2 cursor: 40), never with arithmetic on count. count is a page-size hint, not a strict size: 1/2/5 returned exactly that many items on the first page, a later page returned 8 for count=5, and 10/20/50 were all server-capped at 17. Measured 2026-10-21 with the pure-Go (device-free) signer: 11 videos (940-944 KB) on one place, 17 videos (1.4 MB) on another. The route exposes no sort control: sort_type and order were measured and did not change the page or its order. The upstream throttles bursts, so paced clients are expected. The route is not signature-gated, so it does not need the device-backed signer.

Input Schema

NameRequiredDescriptionDefault
countNoPage-size hint: 1-50 measured, server caps larger pages (default is the app default)
cursorNoNext-page token from the previous response (0 = first page)
poi_idYesPlace id from the place search endpoint

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.16

TDQS

A4.6/5.0
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 unusually well: it discloses the response envelope (aweme_list with full video objects, item_count as page size), that there is no sort control (sort_type/order measured ineffective), that the upstream throttles bursts, and that no device-backed signer is required. These are exactly the operational facts an agent cannot get from the schema.

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?

Front-loaded with the purpose and pagination rule before the empirical detail, and nearly every sentence carries actionable information. Some measurement trivia (KB sizes, exact test date) is expendable, keeping it just short of a 5.

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?

There is no output schema, and the description compensates fully by naming the response keys and what they hold, plus pagination and throttling behavior. An agent has everything needed to call this correctly and interpret the result without guessing.

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 the baseline is 3, but the description adds real meaning beyond it: `cursor` is a reusable next-page token (not an offset to compute), `count` is a hint that can be over- or under-served (count=5 returned 8; 10/20/50 capped at 17). That measurably improves how an agent paginates versus the schema alone.

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+scope: 'Videos posted at one place (paged)', immediately distinguishing it from siblings like tiktok_mobile_place_photos, tiktok_mobile_place_detail, and tiktok_mobile_search_place. It also names the upstream route and the key input source (poi_id from the place search endpoint), so an agent knows exactly what this returns and where the id comes from.

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 concrete operating instructions: page with `cursor`, never with arithmetic on `count`, and that poi_id must come from the place search endpoint. It does not explicitly state when to prefer this over sibling place tools (photos, detail), but the resource-specific framing makes the selection obvious.

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