Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

datasets_vehicle_listings_search

Search vehicle listings dataset. Searches the crawled used-vehicle listings index. source enum: carmax, autotrader, carsdotcom.

Instructions

Search vehicle listings dataset. Searches the crawled used-vehicle listings index. source enum: carmax, autotrader, carsdotcom. CarMax's own national inventory is fully enumerable (re-crawled on a standing schedule); Autotrader/Cars.com coverage is a best-effort zip-code sweep, not exhaustive, and their rows approximate city/state from the searched area rather than the seller's exact location. seller_type enum: retailer, dealer, private (not populated for every row -- see the dataset markdown). Sort enum: relevance, recently_updated, newly_listed, price_asc, price_desc, mileage_asc, mileage_desc, year_desc, year_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

NameRequiredDescriptionDefault
qNoFull-text query over make, model and trim, max 256 characters
vinNoExact VIN filter. Best-effort: not guaranteed on every listing
makeNoExact make filter (e.g. Honda, Toyota), max 128 characters
pageNoPage number, defaults to 1
sortNoSort enum: relevance, recently_updated, newly_listed, price_asc, price_desc, mileage_asc, mileage_desc, year_desc, year_asc
trimNoExact trim filter, max 128 characters
modelNoExact model filter (e.g. Civic), max 128 characters
stateNoExact US state abbreviation filter (e.g. CA), max 8 characters
run_idNoExact crawl run-id filter, max 128 characters
sourceNoExact source marketplace filter: carmax, autotrader, carsdotcom
max_yearNoMaximum model year
min_yearNoMinimum model year
fuel_typeNoExact fuel type filter (e.g. Gas, Hybrid, Electric), max 128 characters
max_priceNoMaximum price in US dollars
min_priceNoMinimum price in US dollars
page_sizeNoPage size, defaults to 20 and maxes at 100; page * page_size must be <= 10000
body_styleNoExact body style filter (e.g. Sedan, SUV), max 128 characters
drive_typeNoExact drivetrain filter, max 128 characters
max_mileageNoMaximum odometer mileage
seller_typeNoExact seller type filter: retailer, dealer, private
transmissionNoExact transmission filter, max 128 characters
is_price_reducedNoFilter for listings currently marked down from a previous price

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.17.5
    • addedInput schema / properties / seller_type / enum
      Added value: +[
+  "retailer",
+  "dealer",
+  "private"
+]
    • addedInput schema / properties / sort / enum
      Added value: +[
+  "relevance",
+  "recently_updated",
+  "newly_listed",
+  "price_asc",
+  "price_desc",
+  "mileage_asc",
+  "mileage_desc",
+  "year_desc",
+  "year_asc"
+]
    • addedInput schema / properties / source / enum
      Added value: +[
+  "carmax",
+  "autotrader",
+  "carsdotcom"
+]
  2. Addedv1.16.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations provided, the description carries the full behavioral burden and does well: it discloses per-record billing with a minimum charge, the enumerability difference between CarMax and the best-effort Autotrader/Cars.com sweeps, and that location is approximated. It stops short of stating rate limits or pagination beyond what the schema already documents.

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, then caveats, then billing. Efficient overall, though the verbatim re-listing of the source, seller_type and sort enums is redundant with the schema and adds length without value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 22-parameter search with no annotations and no output schema, the description covers purpose, cost model, and the key data-quality caveats needed to interpret results. It is largely complete, with the main omission being no guidance on how to page through large result sets or when to prefer sibling tools.

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, and the description earns above that by adding meaning to parameters the schema cannot: that seller_type is not populated for every row, and that source coverage and location semantics differ by marketplace. The enum restatements themselves duplicate the schema and add nothing.

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?

States a specific verb ('Search') plus resource ('crawled used-vehicle listings index'), which is clear and actionable. It doesn't name or distinguish itself from close siblings like datasets_vehicle_listings_facets or datasets_vehicle_listings_item, so an agent gets the purpose but not the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the search framing and the credit-cost warning, but there is no explicit when-to-use versus alternatives (facets for browsing, item for a single listing, price_history for trends). The source-coverage notes help scope it but don't route the agent between siblings.

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