Skip to main content
Glama

Get departures

get_departures
Read-onlyIdempotent

Use for 'which platform' and 'what is leaving' questions at a station. Returns the next departures with the platform if it has been released, otherwise a prediction with confidence that never exceeds the measured accuracy of its group and can be lower. The typical percentage is the measured accuracy in the nearest estimated time-to-release group for that station, shown only when the group has at least 30 results. Each train has a status: due_now means its expected time has passed with no recorded departure, and platform_withdrawn means an announced platform was withdrawn and no number is shown. Absent fields mean unknown. Departed trains are hidden unless include_departed is true, and trains more than 15 minutes past their expected time with no departure are dropped. Times are London local with offset. Filter by operator, destination or window_min. A long board is shortened with a note saying how many trains are not shown; narrow with window_min, operator or destination. Read only. Predictions are unofficial and may be wrong. Station screens are the official source.

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": "get_departures"
  }
}

Input Schema

NameRequiredDescriptionDefault
stationNoStation code, for example EUS or PAD. Default EUS. Call list_stations to see which are live.
operatorNoPartial name or short form, for example Avanti or LNR.
window_minNoMinutes ahead, from 1 to 90. Default 90.
destinationNoSubstring or station code, for example MAN.
include_departedNotrue also returns trains with a recorded actual departure.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / station / description
      Previous value: -"Station code, for example EUS. Default EUS."New value: +"Station code, for example EUS or PAD. Default EUS. Call list_stations to see which are live."
    • addedInput schema / properties / window_min / description
      Added value: +"Minutes ahead, from 1 to 90. Default 90."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent and open-world behavior, yet the description adds substantial non-obvious detail: status semantics (due_now, platform_withdrawn), confidence capped at a group's measured accuracy, the 30-result threshold for showing a typical percentage, absent fields meaning unknown, the 15-minute drop rule, and the truncation note on long boards. It also flags that predictions are unofficial and that station screens are authoritative.

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 use case is front-loaded and every subsequent sentence conveys operative behavior (statuses, confidence, dropping rules, truncation). It is dense and slightly sprawling in the middle where prediction/percentage mechanics are interleaved, but nothing is redundant filler.

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 no output schema, the description carries the full burden of explaining return values, and it does: platform-vs-prediction, confidence semantics, per-train statuses, unknown-field convention, hidden departed trains, time zone, and truncation behavior. An agent has enough to call it and interpret the response correctly.

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 extra by explaining parameter effects on output rather than restating types — include_departed un-hides departed trains, and window_min/operator/destination both filter and control board truncation.

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?

Opens with a specific use case ('which platform' and 'what is leaving' questions) and a concrete resource outcome: 'Returns the next departures with the platform if it has been released.' An agent can immediately tell this is a station departure-board tool, distinct from a single-train lookup like get_train.

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?

Gives clear when-to-use framing ('which platform' / 'what is leaving' questions) and practical narrowing advice ('narrow with window_min, operator or destination'). It does not name sibling alternatives for related questions (e.g., a specific train's details), so it stops short of explicit when-not/alternative routing.

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