Skip to main content
Glama

Vehicle listings from AutoTrader.ca: up to 20 per page

auto_autotrader
Read-only

Vehicle listings from AutoTrader.ca (Canada; the US and UK AutoTrader sites block datacenter traffic): up to 20 per page with title, year, make, model, trim, price in CAD, AutoTrader's price label, mileage in km, transmission, fuel, new/used, dealer, city, province and URL, plus the total matching count and min/median/max price of the page. Filter by make, model, province and city. Related tools on this server, for a different need: auto_carsdirect_vehicle when you need CarsDirect used-car listings near a US ZIP code: vehicle; auto_carfax when you need CARFAX used-car listings by body style or price ceiling. Price: $0.002 per successful call, paid with x402 (USDC on Base, Solana and 10 more networks); failed calls are not charged.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "auto_autotrader"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNoCity, e.g. toronto, vancouver (needs province)
makeNoMake as in AutoTrader.ca URLs, e.g. ford, honda, toyota (optional)
pageNoResult page, 1 to 50 (default 1)
modelNoModel as in AutoTrader.ca URLs, e.g. f-150, civic (needs make)
provinceNoProvince code: ab, bc, mb, nb, nl, ns, nt, nu, on, pe, qc, sk, yt (optional)

Output Schema

NameRequiredDescriptionDefault
pageNo
countNo
titleNo
sourceNo
listingsNo
checkedAtNo
totalPagesNo
totalResultsNo
pagePriceSummaryNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly and openWorld, but the description adds genuinely new behavior: datacenter blocking for US/UK sites, a 20-per-page cap, and the billing model ($0.002 per successful call via x402/USDC, failed calls free). The only gap is that pagination limits are restated from the schema rather than expanded (e.g., what page 50 does when fewer results exist).

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-loads the source, scope and page size before field list, alternatives and pricing, so the critical facts come first. It runs long and the sibling-comparison clauses are wordy, but no sentence is filler.

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?

An output schema exists, so return fields did not need spelling out, yet the description still summarizes them alongside the total-count and min/median/max page price aggregates. Combined with the cost model, geo restriction and filters, an agent has everything needed to decide and call 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 coverage is 100% and already documents the city-needs-province and model-needs-make dependencies, so the baseline is 3. The description names the filterable dimensions (make, model, province, city) but adds no new syntax or matching behavior beyond 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?

States a specific verb and resource ('Vehicle listings from AutoTrader.ca'), the Canadian scope, and the exact record shape (title, year, make, model, trim, price CAD, mileage km, transmission, fuel, condition, dealer, location, URL). An agent can distinguish this from the CarsDirect and CARFAX siblings 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 Guidelines5/5

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

Explicitly routes the agent: use auto_carsdirect_vehicle for used-car listings near a US ZIP code and auto_carfax for CARFAX listings by body style or price ceiling, both framed as 'for a different need'. It also states when this tool is not usable (US/UK AutoTrader sites block datacenter traffic).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources