Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

datasets_airbnb_search

Search the Airbnb markets dataset. Returns aggregate Airbnb short-term-rental market rollups from the dataset id enum value airbnb-markets. Aggregate-only: each row is a market cell, never an individual listing.

Instructions

Search the Airbnb markets dataset. Returns aggregate Airbnb short-term-rental market rollups from the dataset id enum value airbnb-markets. Aggregate-only: each row is a market cell, never an individual listing. Thin cells are suppressed. group_by enum: country, market, admin1 (top subdivision), locality (settlement), room_type (entire_place/private_room/hotel/shared_room), property_type (Airbnb's canonical listing type from the detail page). admin1, locality, room_type and property_type are enrichment-derived and stay empty until their coverage is high enough to be reliable. Each cell also carries median_price_usd, the median nightly price converted to USD via an approximate dated FX snapshot, for cross-country comparison (combine with group_by=room_type for median price by room type); guest_favorite_pct, the share of listings carrying the Guest Favorite badge (an observed lower bound, like superhost_pct); and avg_person_capacity, the average guests a listing sleeps over the detail-page-enriched sample. Sort enum: listings_desc, superhost_pct_desc, rating_desc, key_asc. Billing: this search costs 1 credit per record returned, with a minimum of 2 (an empty result costs 2, a full page of 100 costs 100).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoPage number, defaults to 1
sortNoSort enum: listings_desc, superhost_pct_desc, rating_desc, key_asc
marketNoExact metro-market filter, e.g. Paris, max 128 characters
countryNoExact ISO-3166-1 alpha-2 country filter, e.g. FR
group_byNoAggregate cell dimension enum: country, market, admin1, locality, room_type, property_type. Defaults to country
page_sizeNoPage size, defaults to 20 and maxes at 100; page * page_size must be <= 10000
superhostNoCount only Superhost listings
min_ratingNoMinimum listing rating, from 0 through 5
active_sinceNoFreshness filter, an ISO-8601 date (YYYY-MM-DD); only listings last seen on or after it are counted
min_listingsNoMinimum listings per cell; raises the small-cell suppression floor (never lowered below the built-in minimum)
guest_favoriteNoCount only Guest Favorite listings (an observed lower bound; the badge under-counts)
min_review_countNoMinimum listing review count, 0 or greater

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.17.5
    • addedInput schema / properties / group_by / enum
      Added value: +[
+  "country",
+  "market",
+  "admin1",
+  "locality",
+  "room_type",
+  "property_type"
+]
    • addedInput schema / properties / sort / enum
      Added value: +[
+  "listings_desc",
+  "superhost_pct_desc",
+  "rating_desc",
+  "key_asc"
+]
  2. Changed2 schema fields changedv1.5.0
    • changedInput schema / properties / group_by / description
      Previous value: -"Aggregate cell dimension enum: country, market. Defaults to country"New value: +"Aggregate cell dimension enum: country, market, admin1, locality, room_type, property_type. Defaults to country"
    • addedInput schema / properties / guest_favorite
      Added value: +{
+  "description": "Count only Guest Favorite listings (an observed lower bound; the badge under-counts)",
+  "type": "boolean"
+}
  3. Addedv1.2.0

TDQS

A4.6/5.0
Behavior5/5

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

No annotations are provided, so the description carries the full burden, and it delivers: thin-cell suppression, enrichment-derived fields staying empty until coverage is reliable, median price coming from an approximate dated FX snapshot, guest_favorite_pct being an observed lower bound, and explicit billing (1 credit per record, minimum 2).

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?

Purpose is front-loaded in the first sentence, and the dense enumeration of group_by values and cell fields all carries necessary meaning. It is long, but nearly every clause adds information an agent needs, so the length is justified rather than padding.

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 12-parameter tool with no output schema and no annotations, the description fills the gaps: it names the returned cell metrics, explains suppression and enrichment-coverage caveats, and documents the cost model. Nothing critical to correct invocation is missing.

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 the schema by explaining what the enum values denote (`admin1` = top subdivision, `locality` = settlement, property_type = canonical listing type) and how group_by interacts with the returned metrics.

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 the Airbnb markets dataset') and immediately scopes it as 'aggregate Airbnb short-term-rental market rollups' from the `airbnb-markets` dataset id. It explicitly distinguishes itself from listing-level tools ('each row is a market cell, never an individual listing').

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 context (aggregate market rollups, combine with `group_by=room_type` for median price by room type) and implicitly excludes listing-level use. However, it never names a sibling alternative (e.g. an item/nearby/facets tool) for when the agent wants individual listings or facet browsing.

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