Skip to main content
Glama

Buscar obras de arquitectura

buscar_obras
Read-onlyIdempotent

Use this when the user asks what architecture to see in a city, a neighbourhood or near a place, for buildings by an architect or a studio, of a type, style, material or period, or for ideas for an architecture trip or walk. Searches the more than 32,000 works in Builtalist, from all over the world, and gives up to 20, the most notable first (essential, then featured), each with its architects, year, place and link, plus a link to see them all on the Builtalist map. All filters are optional and combine.

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": "buscar_obras"
  }
}

Input Schema

NameRequiredDescriptionDefault
paisNoA country, in English or Spanish: Portugal, Japan, United States, España.
cercaNoAround a point, for "near me" or "near this place".
desdeNoBuilt in this year or later. Years BC are negative.
hastaNoBuilt in this year or earlier.
ordenNoWith "cerca", "cercanas" sorts by distance. By default, the most notable first.
rangoNoesencial: only the essential works (the must-sees of their city); destacada: the essential and the featured ones.
textoNoWords to look for in the name, the architects, the neighbourhood, the city and the keywords of each work (materials, features and uses: glass, brick, courtyard, cantilever, church, library…), in English or Spanish. With several words, works with more of them come first.
ciudadNoA city, by its English name as in the catalogue: Porto, Lisbon, Munich, New York, Rome.
limiteNoHow many works to give, from 1 to 20. 10 if not given.
etiquetasNoOnly works with all these tags: CON = exposed concrete, LAD = brick, MAD = wood, PIE = stone, ArtDeco = Art Deco, Brutalism = Brutalism, ChicagoSchool = Chicago School, Eclecticism = Eclecticism, Georgian = Georgian, Gothic = Gothic, Historicism = Historicism, InternationalStyle = International Style, Modernism = Modernism, Neoclassicism = Neoclassicism, Postmodernism = Postmodernism, Rationalism = Rationalism, RenaissanceBaroque = Renaissance and Baroque, SecondModernity = second modernity, Victorian = Victorian, CNC = came out of a competition, COM = commercial, CUL = cultural, EDU = education, GOV = civic, HOT = hospitality, IND = industrial, INT = interior design, MIX = mixed use, MUS = museum, PUB = public space, REL = religious, RES = housing, Reuse = adaptive reuse, SIN = special-purpose building, SPO = sports, TMP = temporary architecture, TRA = transport.
visitableNoOnly works that can be visited inside.
arquitectoNoAn architect or a studio, or part of the name: "Siza", "Herzog & de Meuron", "Lina Bo Bardi".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already mark this as a safe idempotent read, and the description adds genuinely new behavior: results are capped at 20, ordered most-notable-first (essential then featured), each item carries architects, year, place and a link, plus a supplementary map link for the full set. 'All filters are optional and combine' also discloses the AND-combination rule, which is not visible anywhere in the structured fields.

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?

Front-loaded with the trigger condition, followed by what is searched, then what comes back. No filler sentences; every clause (dataset size, cap of 20, ordering, per-item fields, map link, optional-combining filters) is information an agent needs.

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 12 parameters, a nested geo object, no output schema and rich annotations, the description covers the remaining gaps: result volume, ordering, item shape and an escape hatch to the full set. Nothing an agent needs in order to call it or to describe its output to a user is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description earns one more by stating that filters are all optional and combine cumulatively, which clarifies how the twelve parameters interact. It does not add per-parameter detail (e.g. how 'texto' ranking interacts with 'orden'), so it is not a full 5.

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 ('Searches the more than 32,000 works in Builtalist') and enumerates the exact query shapes it accepts: city, neighbourhood, near a place, architect/studio, type, style, material, period, or trip ideas. An agent can distinguish this from the sibling concurso/exposición/historia searches without opening any schema.

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 opening sentence gives a strong, concrete when-to-use trigger list tied to user phrasings ('what architecture to see in a city... near a place... by an architect or a studio'). It stops short of naming a sibling alternative or stating when-not to use it, so it falls just below the explicit-alternatives bar.

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