Cinve

Consultar funciones

get_showtimes

Read-onlyIdempotent

Consulta funciones de una fecha (hoy en Caracas por defecto). Cinepic requiere cinema_id (123300 Candelaria o 123301 VVIP Lido); Cines Unidos city; Cinex acepta city para todas sus sedes verificadas de la ciudad en una llamada, cinema_id para una sede (con movie_id opcional para filtrar), o solo movie_id para consultar la ficha de la película en todas las sedes; Supercines acepta cinema_id, city o movie_id; Gran Cine (cine de autor, incluye las salas del Paseo Las Mercedes) acepta cinema_id, city o ninguno para todas sus salas, sin IDs de función del proveedor; usa query para filtrar por título. La llamada de sede resuelve títulos contra el catálogo y marca partial cuando no puede confirmar un movie_id. Retorna IDs necesarios para tarifas, sala/formato cuando disponibles y URL de la web.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "provider": "<provider>"
    },
    "name": "get_showtimes"
  }
}

Input Schema

Name	Required	Description
`city`	No	Nombre de ciudad tal como lo devuelve list_cities del mismo proveedor (p. ej. Caracas); no distingue tildes ni mayúsculas en Cines Unidos.
`date`	No	YYYY-MM-DD; por defecto hoy en America/Caracas para películas y funciones de Cinepic/Cines Unidos y funciones de Cinex, Supercines y Gran Cine.
`limit`	No
`query`	No	Filtra por nombre, sin distinguir tildes/mayúsculas.
`offset`	No
`refresh`	No	true: consulta al proveedor sin usar caché local; solicita revalidación HTTP. No garantiza que el proveedor haya actualizado su contenido.
`movie_id`	No	ID de película devuelto por list_movies del mismo proveedor; opcional en Cinex cuando se consulta una sede completa.
`provider`	Yes	Proveedor de cine; obtén capacidades y limitaciones con list_providers.
`cinema_id`	No	ID de sede devuelto por list_cinemas del mismo proveedor. No mezcles IDs entre proveedores. Si la sede incluye code_status, usa cinema_id solo cuando sea verified; los IDs directory-* no permiten consultas.

Output Schema

Name	Required	Description	Default
`items`	Yes
`total`	Yes
`status`	Yes
`partial`	Yes
`sources`	Yes
`provider`	Yes
`timezone`	Yes
`warnings`	Yes
`queried_at`	Yes
`next_offset`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 11, 2026

TDQS

A4/5.0

Behavior4/5

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

With readOnly/openWorld/idempotent annotations already covering the safety profile, the description adds genuinely new behavior: the Caracas/timezone default for date, the 'partial' flag raised when a venue call cannot confirm a movie_id, and the fact that venue calls resolve titles against the catalog. It does not discuss rate limits or what 'partial' means for downstream consumers, but the disclosure goes well beyond the annotations.

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

Conciseness3/5

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

The purpose and default are front-loaded, and every clause carries information, but the body is one long semicolon-chained block that an agent must parse carefully to extract per-provider rules. A short structured breakdown of provider → accepted parameters would convey the same content with less reading risk.

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?

For a 9-parameter, 5-provider tool with an output schema, the description covers the hard parts: provider-specific argument combinations, the date default, the partial-result caveat, and what the response carries (pricing IDs, sala/formato, web URL). Pagination and refresh semantics are already documented in the schema, so nothing an agent needs to call this correctly 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 78%, so the baseline is 3; the description earns above that by mapping parameters to provider capabilities (which provider needs cinema_id vs city vs movie_id) and by explaining that query filters by title. That is real meaning not present in the schema, where each parameter is described only in isolation.

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 first clause states a specific verb and resource ('Consulta funciones de una fecha') with a default scope (hoy en Caracas), which is far more precise than the title. It never names a sibling, and the Cinex 'solo movie_id' mode blurs the line with list_movies by returning a film's ficha rather than showtimes, so the boundary needs a little inference.

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 explicit, per-provider parameter rules (Cinepic requires cinema_id with concrete example IDs; Cines Unidos uses city; Cinex/Supercines/Gran Cine accept several combinations), which is exactly the conditional guidance an agent needs before calling. It stops short of naming alternatives such as list_movies for pure film metadata or list_cities for resolving city names, but the when-to-use conditions themselves are clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Cinve tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.