Skip to main content
Glama

Bazaraki classifieds

Search listings

search_adverts
Read-only

Search listings on the marketplace. Results never include seller contacts.

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_adverts"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryNoFree-text search, e.g. 'iphone 15 128gb'.
languageNoLanguage of listing texts: one of en, el. Default en.
locationNoCity or district name.
orderingNo
price_maxNo
price_minNo
attributesNoCategory filters from get_category_filters: {key: value} for select, {key: [values]} for multiselect, {key + '_min' / key + '_max': number} for range.
page_tokenNonext_page_token of the previous result, same filters.
category_idNoCategory from list_categories.

Output Schema

NameRequiredDescriptionDefault
pageYes
totalNoMatching listings, may be capped by the site.
advertsYes
locationNoLocation the search was narrowed to.
next_page_tokenNoPass to search_adverts for more results.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds one genuinely new behavior: contacts are always stripped from results, which pre-empts a false expectation. It omits other behavior the annotations don't cover, such as default page size, the 30-result cap, and that page_token must be reused with identical filters.

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?

Two short sentences, front-loaded with the action and followed by the one non-obvious constraint. No filler. It is efficient, though its brevity is as much under-specification as discipline.

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

Completeness3/5

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

An output schema exists, so return values need not be described, and most parameters are self-documented. Still, for a 10-parameter, zero-required search tool, the definition gives no default-ordering note, no pagination guidance, and no category-filter workflow, leaving an agent to infer the search-to-reveal_contact path on its own.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description mentions no parameters at all. Schema description coverage is 60% — the substantive ones (query, location, attributes, page_token, category_id, language) are documented in-schema, but limit, ordering, price_min and price_max are described nowhere except by name. That is below the high-coverage baseline, and the description contributes zero compensation.

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 listings on the marketplace.' That clearly separates it from the singular get_advert and from list_categories/get_category_filters by verb alone. It stops short of explicitly naming which sibling to use next, but the purpose is unambiguous.

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?

The description does not say when to use this versus get_advert (single listing) or how to drive follow-up calls. The clause 'Results never include seller contacts' implicitly signals that reveal_contact is required for contacts, which is useful routing but is never stated as guidance.

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