Skip to main content
Glama

Entur

by io.github.pipeworx-io

Entur Departures

entur_departures
Read-onlyIdempotent

Real-time departures board for any public-transport stop in Norway — train, tram, metro, bus, and ferry departures for Oslo, Bergen, Trondheim, Stavanger and every other Norwegian stop, from Entur (the national journey-planning authority covering Vy, Flytoget, Ruter, Skyss, AtB, formerly NSB). Returns line, destination, aimed vs expected time, delay in minutes, platform/quay, and realtime flag. Example: entur_departures({ stop: "Oslo S", mode: "rail" })

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoOptional transport-mode filter. "water" = ferry/boat, "rail" = train.
stopYesStop or station name, e.g. "Oslo S", "Bergen stasjon", "Trondheim S", "Jernbanetorget" — or a raw NSR id like "NSR:StopPlace:59872"
limitNoMax departures to return, 1-50 (default 10)

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds value by specifying the exact data returned (line, destination, times, delay, platform, realtime flag) and confirming real-time nature, which is not detailed in annotations.

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?

The description is extremely concise: two sentences plus an example code snippet. Every sentence adds value without redundancy. It is front-loaded with the core purpose.

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?

Given the tool's simplicity (3 parameters, no output schema), the description fully covers what a user needs to know: scope, usage, returned fields, and an example. No gaps remain.

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 has 100% description coverage. The description further enhances semantics by including an example that demonstrates the stop and mode parameters, and explains mode enums (e.g., 'water = ferry/boat, rail = train'). Default limit of 10 is mentioned.

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?

The description explicitly states it is a real-time departures board for any public-transport stop in Norway, listing modes and providing an example. This clearly differentiates it from sibling tools like entur_journey (journey planning) and entur_stops_search (stop lookup).

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 includes a clear usage example and implies its use for retrieving departures for any Norwegian stop. While it does not explicitly state when not to use it compared to siblings, the specific focus on departures provides sufficient guidance.

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

All Entur 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
Disambiguation2/5

Although many tools are individually well-described, there are several overlapping clusters: three ask_pipeworx variants, multiple polymarket edge/arbitrage tools, and AI-visibility checks vs their competitor-comparison wrapper. An agent can easily pick the wrong one because the boundaries (beta vs stable, grounded vs routed, edge vs arbitrage) are subtle despite the verbose descriptions.

Naming Consistency3/5

The set is consistently snake_case and mostly readable, so naming is not chaotic. However, the pattern is mixed: some tools use entur_/polymarket_/pipeworx_ prefixes, others are bare verbs (remember, recall, forget), and some are noun phrases (entity_profile, pipeworx_trending). The ask_pipeworx family also doesn't follow the pipeworx_ prefix convention used by neighboring tools.

Tool Count2/5

34 tools is well past the healthy range for a focused MCP server, and only three tools relate to the Entur transport domain implied by the server name. The other 31 tools form a separate, broad data/prediction-market product that appears bolted on, making the count inappropriate for the apparent purpose.

Completeness2/5

The Entur transport subset has stops search, departures, and journey planning, but misses common public-transport needs such as disruptions, service alerts, and fare/ticket information. The broader tool set is extensive but lacks a single coherent domain to be complete against, leaving the overall surface scattered and hard to trust as an integrated whole.

Resources