Skip to main content
Glama
Crawlora MCP

Crawlora MCP

Official

tiktok_mobile_place_detail

Retrieve a TikTok place-detail page by poi_id, including address, hours, rating, photos, top videos, posts, reviews, and AI summaries for building POI screens.

Instructions

Place (POI) detail from the mobile app's Places surface. Returns one place detail page, keyed by the poi_id that the place search endpoint returns. The upstream is TikTok's server-driven UI (/tiktok/poi/slash/v1) frame stream, assembled here into the component map of the place-detail screen: food_head_info (place name, formatted address, category, phone, coordinates, opening hours, rating/score with mention count, price range, tags and photo album), poi_top_videos (top videos strip), poi_limited_post (posts about the place: full video items plus aweme_cursor/has_more_aweme), poi_review (review preview with has_more) and ai_summary when the place has one. nodes is opaque and complete, frames keeps the raw ordered frames, and the typed counters (top_video_count, post_count, post_cursor, has_more_posts, review_count, has_more_reviews) are convenience projections. The measured page-size controls are forwarded with the app's defaults but the server applies its own bounds.

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": {
      "poi_id": "<poi_id>"
    },
    "name": "tiktok_mobile_place_detail"
  }
}

Input Schema

NameRequiredDescriptionDefault
poi_idYesPlace id from the place search endpoint
enter_fromNoForwarded analytics origin (default search_places)
merged_countNoPosts page size forwarded upstream (default 9, bounded at 50)
review_countNoReview preview size forwarded upstream (default 20, bounded at 50)
video_cursorNoTop-videos cursor forwarded upstream (default 0)
review_cursorNoReview cursor forwarded upstream (default 0)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.16

TDQS

A4.1/5.0
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 names the upstream server-driven UI endpoint, explains that the result is assembled into a component map, discloses that nodes is opaque and complete, that frames preserves raw ordered frames, and that page-size controls are forwarded but bounded server-side. It also lists the key component sections and convenience counters, giving an agent a strong behavioral picture before invocation.

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?

The purpose is front-loaded and the long detail is largely justified because there is no output schema and the return structure is complex. It is dense and could be more readable with structure, but most of the information earns its place.

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 six-parameter detail tool with no annotations and no output schema, the description is complete enough: it explains the required ID source, the upstream frame-based origin, the assembled component map, raw frame behavior, convenience counters, and server-side bounds. An agent has what it needs to select and invoke the tool correctly.

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 description coverage is 100%, so the baseline is 3. The description mostly repeats what the schema already documents, such as poi_id provenance and the fact that page-size controls have defaults and upstream bounds; it adds little parameter-level meaning beyond the schema.

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?

The description states a specific verb and resource: it returns a place/POI detail page from TikTok's mobile Places surface, keyed by the poi_id produced by place search. This clearly separates it from search/list endpoints, though it does not explicitly distinguish it from close siblings such as tiktok_mobile_place_info or the photo/video place tools.

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 gives a clear prerequisite by saying the tool is keyed by the poi_id that the place search endpoint returns, which tells an agent to obtain the ID from search first. It does not explicitly name alternatives or exclusions, so it stops short of full when-to-use/when-not guidance.

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