highbrow_fame data APIs (pay per call)

Live listings on OfferUp or Craigslist

classifieds_search

Read-only

Live second-hand listings from OfferUp or Craigslist in the United States. Searches by keyword and location and returns title, price, location, posting time, link and image, plus description, condition and category where shown. Suited to second-hand price checks, deal finding and resale research. $0.02 per call, up to 25 listings.

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": "classifieds_search"
  }
}

Input Schema

Name	Required	Description
`zip`	No	craigslist only: search around this 5-digit ZIP code inside the city site; use radius for the distance.
`site`	No	craigslist or offerup.
`limit`	No	Maximum listings (1 to 50, default 20).
`query`	No	Search words, up to 100 characters, e.g. "road bike". Optional: without it you get the listings of the location and category.
`radius`	No	Distance in miles. offerup: 5, 10, 20, 30 (default 30). craigslist: 1 to 500, only together with zip.
`details`	No	craigslist only (default false): open every listing for its description and condition. Slower. offerup always includes them.
`category`	No	A category of the chosen site. craigslist: sss (for sale, default), cta (cars & trucks), hhh (housing), apa (apartments for rent), rea, roo, sub, jjj (jobs), ggg (gigs), bbb (services), fua (furniture), ela (electronics), bia (bicycles), mca (motorcycles), zip (free). offerup: electronics-and-media,
`location`	No	Where to search. offerup: a US city ("Austin, TX") or a 5-digit ZIP code (98101). craigslist: one of its city sites: sfbay, newyork, losangeles, chicago, seattle, austin, boston, denver ... (or the name, e.g. "SF bay area", or a sub-area such as manhattan). Craigslist does not take a ZIP code here:
`maxPrice`	No	Maximum price in whole dollars.
`minPrice`	No	Minimum price in whole dollars.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Beyond readOnlyHint/openWorldHint it adds real behavioral facts: $0.02 per call, a listing ceiling, US-only coverage, and that details=true on craigslist is slower. One flaw: "up to 25 listings" conflicts with the schema's limit of 1–50 (default 20), which could mislead an agent about the achievable result count.

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?

Four short sentences, front-loaded with what the tool is, then returns, use case, and cost. Nothing is padded, but the "up to 25 listings" ceiling is both extraneous given the limit parameter and inconsistent with it.

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 10-parameter, zero-required search tool with no output schema, the description covers source, geography, returned fields, cost and the main site-dependent behavior. The remaining gaps (pagination, empty-result handling) are minor, and per-parameter nuances are already fully covered by the schema.

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 the schema already explains site, zip, radius, details, category codes and location formats in more detail than the description. The description only adds the return-field mapping ("description, condition and category where shown"), which is modest value over a fully documented schema, so baseline 3 applies.

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?

"Live second-hand listings from OfferUp or Craigslist in the United States" names the exact resource and sources, and "Searches by keyword and location" supplies the verb. It also enumerates the returned fields, and the domain is distinct enough that an agent will not confuse it with jobs_search, properties_search or the grocery_* 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?

"Suited to second-hand price checks, deal finding and resale research" gives concrete when-to-use context, and "Live" plus the US restriction implicitly signals when not to use it (stale or non-US data). It stops short of naming an alternative tool or stating explicit exclusions, so it is clear but not fully routing-aware.

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

All highbrow_fame data APIs (pay per call) tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?