Skip to main content
Glama

mcp-server

by com.vamosalicante

Próximas salidas y llegadas de transporte

next_departures
Read-onlyIdempotent

Próximas llegadas o salidas de un servicio concreto de Alicante: autobús urbano por parada, TRAM por estación, Cercanías/ADIF, autobús interurbano por destino, o la línea C6 del aeropuerto. Requiere identificar el servicio y la parada o el destino. Con mode=bus la consulta extrae SIEMPRE el dato bajo demanda desde la fuente oficial del Ayuntamiento de Alicante / «Alicante se mueve» mediante /api/public/v1/bus/live-arrivals. Si falla el LIVE, el único fallback es estimated_eta del motor predictivo propio, claramente ESTIMATED.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dateNoFecha YYYY-MM-DD (Europe/Madrid) para tram o coach.
lineNoLínea concreta, solo para mode=bus.
modeYesServicio: bus urbano, TRAM, tren, autobús interurbano o C6 del aeropuerto.
stopNoCódigo de parada de bus (mode=bus) o identificador de estación TRAM (mode=tram).
typeNoSolo para mode=train: departures | arrivals | all (alias: salidas, llegadas).
destinationNoDestino, solo para mode=coach.

TDQS

A4.1/5.0
Behavior5/5

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

Even though annotations already mark the call as read-only/idempotent, the description adds real operational transparency: it names the official live endpoint, says the bus query always hits it on demand, and reveals the exact fallback (`estimated_eta`) with an explicit ESTIMATED label. This is exactly the kind of behavioral context annotations cannot convey.

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?

The purpose, preconditions, and bus-specific behavior are front-loaded in four dense sentences with no filler. The endpoint path is specific but earns its place by clarifying the authoritative source.

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?

With no output schema, the description doesn't describe the response shape or fields beyond mentioning `estimated_eta` in fallback. It also omits error/rate-limit behavior and how to resolve stop identifiers, so while it's adequate for invocation, it has clear completeness gaps.

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?

Input schema descriptions cover 100% of parameters, so the baseline is already solid. The description adds extra semantic meaning by mapping 'servicio' to mode and 'parada o destino' to stop/destination, and by explaining the live-vs-fallback behavior that affects how mode=bus results should be interpreted.

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 opening sentence names the resource ('servicio concreto de Alicante') and enumerates the five transport modes (bus, TRAM, Cercanías/ADIF, coach, C6), so an agent can tell this is a transit-query tool. It lacks an explicit main verb such as 'return' or 'get' and does not name sibling tools for differentiation, so it stops just short of top score.

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 description states the precondition clearly: 'Requiere identificar el servicio y la parada o el destino' and explains mode=bus behavior. It does not mention when to prefer a sibling like find_transit_stop to obtain missing stop/destination codes or when to avoid the tool.

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

All mcp-server toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation3/5

Several tools overlap in purpose: find_transit_stop and resolve_entity both resolve stops, while get_current_state, next_departures, favorite_stop, parking_availability, and beach_conditions all provide state/arrival information in different forms. The detailed descriptions help, but an agent could easily select the wrong tool when asked for simple arrival or status information.

Naming Consistency3/5

All names use snake_case and are readable, but the pattern is mixed: some are verb-led (find_place, get_current_state, resolve_entity), some are noun phrases (beach_conditions, fuel_prices, flight_status), and others are quirky (whats_on, catch_vehicle_decision). This is not chaotic, but it lacks a strong consistent convention.

Tool Count4/5

With 16 tools, the server is just above the ideal 3-15 range, but the broad Alicante information domain justifies the count. Each tool covers a distinct vertical or query path, and the set feels reasonably scoped rather than bloated.

Completeness4/5

The tool surface covers the main Alicante information domains well: transit, beaches, parking, food, places, flights, fuel, weather, and events, plus discovery/resolution helpers. There are minor gaps such as no direct traffic or bike-sharing tool, but agents can work around them via find_place or search_alicante.

Resources