Skip to main content
Glama

Find bars, restaurants and cafes

find_places
Read-onlyIdempotent

Find pintxos bars, restaurants, cafes and wineries that Gozatu! has visited and reviewed in Donostia-San Sebastián and the Basque Country. Filter by name or keyword, district, type, opening time ("now" or a date and time) and distance to a point. Each place has its review URL, type, district, coordinates, opening hours for the requested day and whether it is open at that time; restaurant holidays are taken into account. Opening hours come from the author's reviews, not from the venues in real time.

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": "find_places"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoOptional type: bar (pintxos bar), restaurant, cafe, weingut (winery), other (sights and others).
limitNoMaximum number of places (default 8, maximum 25).
queryNoOptional name or keyword, e.g. "Ganbara", "Hondarribia", "Sushi".
open_atNoOptional: "now" or a local date and time such as "2026-12-19T20:30" (Europe/Madrid). Only places open at that time are returned.
districtNoOptional district of San Sebastián, e.g. "Parte Vieja", "Gros", "Centro", "Antiguo", "Egia", "Amara".
near_latNoOptional latitude of a point; results are sorted by distance.
near_lngNoOptional longitude of that point.
radius_mNoOptional radius in metres around the point (default 1000, maximum 50000).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: data comes from the author's reviews rather than live venue data, holidays are accounted for, and each result carries its review URL, coordinates and day-specific opening hours. That provenance caveat is a real addition, though it does not describe pagination or error behavior. Given the annotations already carry the operational traits, a 3 is the fair mark, with the caveat carrying most of the credit.

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?

Three sentences, front-loaded with the core verb and scope before the filter list and the data caveat. Dense but essentially waste-free; the third sentence packs return-field inventory and the holiday/real-time caveat together, which is slightly compressed but still readable.

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?

There is no output schema, and the description compensates by enumerating what each place record contains (review URL, type, district, coordinates, opening hours for the requested day, open-now status). The provenance caveat about non-real-time hours is exactly the kind of thing an agent needs to avoid over-claiming accuracy. Nothing material is missing for an eight-parameter read-only lookup.

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 description coverage is 100%, so the schema already documents all eight parameters including the enum and the 'now' / ISO datetime format. The description restates the filter axes and adds a small amount of meaning ('name or keyword', 'distance to a point', day-specific opening hours), but nothing about syntax or units that the schema doesn't already supply. Baseline 3 applies.

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 ('Find') plus the resource (pintxos bars, restaurants, cafes, wineries) and a tight geographic scope (Donostia-San Sebastián and the Basque Country), plus the defining constraint that these are places the author has visited and reviewed. It does not explicitly differentiate itself from the 'search' sibling, so it stops short of a 5.

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?

The filtering criteria (name/keyword, district, type, opening time, distance to a point) make the intended use case clear: locating a reviewed venue that satisfies practical constraints like being open now. There are no explicit when-not-to-use statements or named alternatives, which keeps it from a 5.

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