Skip to main content
Glama

Us Auctions Search

us_auctions_search
Read-onlyIdempotent

Search live US auction lots across every source Pipeworx indexes, commercial auction houses (HiBid: ~1,900 US auctioneers, industrial liquidations, estate and equipment sales) and government surplus/seized/tax-deed sales (GovDeals, AllSurplus, PublicSurplus, Bid4Assets, IRS). Filter by free-text keyword (matched on the lot title, e.g. "forklift", "excavator", "F-150"), 2-letter state, asset_type (vehicle|equipment|realestate|electronics|other), segment (commercial|government), auction_house, max_price and closing_within_hours, or search geographically with near_zip + radius_miles ("forklifts within 50 miles of 94402"), which returns lots ordered by distance. Keyword search is full-text over the lot title AND description, so "cnc lathe" finds a lot titled "Haas TL-1" whose description says CNC lathe. Returns each lot with source, title, selling house, location, current bid, close time and a link. For what things actually SOLD for, use us_auctions_sold_comps instead.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "limit": 10,
      "keyword": "forklift"
    },
    "name": "us_auctions_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax lots (1-100, default 25).
stateNo2-letter state code of the item location, e.g. "CA", "TX".
sourceNoRestrict to one source: hibid | govdeals | allsurplus | publicsurplus | bid4assets | irs | txauction.
keywordNoFree-text matched (case-insensitive) against the lot title, e.g. "forklift", "skid steer", "mac pro".
segmentNoRestrict to one half of the market: government | commercial. Omit for both.
near_zipNoUS 5-digit ZIP to search around, e.g. "94402". Combine with radius_miles for "what is up for auction near me". Results come back ordered by distance and carry distance_miles.
max_priceNoOnly lots whose current bid is at or below this. Note that a lot with no bids yet has no current bid and is excluded.
asset_typeNoOne of: vehicle | equipment | realestate | electronics | other.
radius_milesNoRadius around near_zip, in miles (1-500, default 50). Ignored unless near_zip is given.
auction_houseNoSelling auctioneer, matched as a substring, e.g. "Silicon Valley Disposition".
closing_within_hoursNoOnly lots closing within this many hours from now.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, open-world behavior, so the safety profile is covered; the description instead adds genuine behavioral detail the annotations cannot: keyword matching runs over both lot title and description (with a Haas TL-1 / "cnc lathe" example), and geo results come back ordered by distance. It also lists the returned fields, which matters because no output schema exists. It stops short of noting rate limits, pagination, or how many sources fail gracefully.

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 core verb and corpus, then filters, then the geographic mode, then return shape, then the sibling redirect — a logical order. It is a single dense paragraph that runs long, but nearly every clause carries filter or behavior information, so little is wasted.

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 an 11-parameter, zero-required, no-output-schema tool, the description covers corpus, filter families, geo semantics, return fields, and the key sibling alternative — enough to call it correctly. Minor gaps: no mention of the source parameter as a distinct control or of how limit/paging interacts with broad queries, though the schema covers limit.

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%, so all 11 parameters are already documented with descriptions and the baseline is 3. The description does add two useful interpretations beyond the schema — the title-plus-description scope of keyword and the fact that near_zip results are distance-ordered — but most parameter prose simply restates schema content with examples rather than adding new semantics.

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 live US auction lots") and enumerates the indexed sources (HiBid, GovDeals, AllSurplus, PublicSurplus, Bid4Assets, IRS), so the agent knows exactly what corpus is being queried. It also explicitly names the sibling it is not (us_auctions_sold_comps) for the sold-price use case.

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?

Gives concrete when-to-use patterns for both search modes: keyword filtering versus geographic search with near_zip + radius_miles, complete with a quoted natural-language example ("forklifts within 50 miles of 94402"). It also states when to go elsewhere: "For what things actually SOLD for, use us_auctions_sold_comps instead."

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.