Skip to main content
Glama

Search restaurants

search_restaurants
Read-onlyIdempotent

Finds restaurants listed in the Yemekhost directory, near a position, in a city or district, or by name, dish or cuisine. Results are restaurant branches with their opening state, rating, distance when a position was given, and whether they deliver to it. Orders are not placed here: every result carries an orderUrl, the restaurant's own page, where the person places the order.

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_restaurants"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNoOnly branches in this city.
pageNoPage number, from 0.
sizeNoResults per page. Default 20, at most 100.
queryNoA restaurant, a dish or a product to look for.
cuisineNoA cuisine name as list_cuisines returns it.
deliveryNoOnly branches that deliver to the position.
districtNoOnly branches in this district; give the city with it.
latitudeNoLatitude of the position, in degrees. Give it together with longitude.
open_nowNoOnly branches that are taking orders now.
longitudeNoLongitude of the position, in degrees. Give it together with latitude.
radius_metresNoSearch radius around the position, in metres. Default 5000, at most 30000.
group_by_brandNoOne result per brand, the nearest branch. Default true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior, so the bar is lower; the description still adds real value by describing the result payload (branches with opening state, rating, distance when a position is given, and delivery eligibility to that position) and by stating that ordering happens elsewhere. It does not mention pagination limits or result-count behavior, which the schema covers only partially.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, both earning their place: the first front-loads what is searched and how, the second states the transactional boundary and where the order link lives. No filler or repetition of the title.

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?

With no output schema, the description carries the burden of describing returns and does so precisely: branch-level results, opening state, rating, conditional distance, delivery eligibility, and orderUrl. Combined with a fully documented schema, an agent has everything needed to call this correctly and act on the results.

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 the schema already documents all 12 parameters including defaults and bounds. The description reinforces the main filter modes and explains that distance is reported only when a position is supplied, but adds no format or interaction detail (e.g. that group_by_brand=true collapses branches to one per brand, changing result counts) beyond the schema.

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?

The description opens with a specific verb and resource ('Finds restaurants listed in the Yemekhost directory') and enumerates the search modes (position, city/district, name/dish/cuisine). It clearly distinguishes discovery from ordering, but never names a sibling such as get_restaurant for single-restaurant detail lookup, so sibling differentiation is only partial.

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?

It gives clear context for when to use it (locating branches by location, area, or text) and an explicit boundary: 'Orders are not placed here', pointing the agent to the per-result orderUrl for the actual transaction. What is missing is guidance on alternatives, e.g. when to prefer get_restaurant once a branch is identified.

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