Skip to main content
Glama

EX & GO marketplace

Search listings

search_listings
Read-only

Search active marketplace listings on EX & GO (exgo.io), the classifieds marketplace for Ukraine and Europe (24 per page). All filters optional. Results marked promoted: true are paid top placements — up to 12 of them come first on page 1, the rest keep their organic position; say they are paid when reporting them, do not present a paid placement as the best match. Under the default new sort a paid BUMP also moves a listing up. When few or no listings matched as asked, the answer carries a related array of the nearest listings — those did not match the query, so report them as "nothing exactly like that, here is what is close", never as stock. Every listing has a url on the site; show it.

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": "search_listings"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNofree-text query, any language
cityNocity slug, e.g. 'kyiv' — or several comma-separated ('kyiv,lviv') to match any of them
pageNo
sortNo'new' (default) orders by freshness, which a paid BUMP resets, then relevance; 'cheap'/'expensive' order by price
categoryNocategory slug, e.g. 'telefony'
maxPriceNohighest price, inclusive, in UAH (other currencies converted), or in `priceCurrency`
minPriceNolowest price, inclusive, in UAH (other currencies converted), or in `priceCurrency`
radiusKmNoradius in km around `city`: also matches listings pinned within it (needs `city`)
attributesNocategory attribute filters, e.g. {"brand":"skoda"}; needs `category`, keys from list_categories
priceCurrencyNoISO 4217 currency of minPrice/maxPrice (default UAH) — converted at the bank's rate like the catalogue's own filter
attributeRangesNonumeric attribute ranges, e.g. {"year":{"min":2015}}; needs `category`, number attributes only

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior5/5

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

Annotations only declare readOnlyHint/openWorldHint, yet the description adds substantive behavior: 24-per-page pagination, up to 12 `promoted: true` placements pinned to page 1, BUMP affecting the default `new` sort, the `related` fallback array when results are thin, and the presence of a `url`. It also gives reporting rules (label paid placements, don't call related items matches) that no annotation covers.

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 purpose and page size, then the caveats that matter. It is dense but almost every sentence carries an operational rule; the only minor redundancy is restating the paid-placement reporting rule twice in one sentence.

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?

With 11 optional params, nested objects, and no output schema, the description must carry return-shape knowledge, and it does explain the promoted flag, the related array, and the url field. It stops short of describing other listing fields (price, location, totals), but an agent has enough to call and report 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 91%, so the schema already carries filter semantics. The description's sort discussion largely restates the schema's own note that `new` is reset by a paid BUMP; it adds nothing about q, city, radiusKm, attributes, or attributeRanges beyond what is documented.

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 and resource ('Search active marketplace listings on EX & GO') plus the domain and page size. It is clearly distinct from get_listing or list_categories in shape, but it never names a sibling, so differentiation is by inference rather than explicit contrast.

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?

'All filters optional' tells the agent a no-parameter call is valid, which is useful. However, there is no explicit when-to-use/when-not guidance or pointer to alternatives (e.g., get_listing for a single item), so selection guidance is only implied.

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