Skip to main content
Glama

check_transit_disruption

Read-onlyIdempotent

Check public-transport punctuality and disruption in a German region: delayed trips, skipped stops, cancellations, trends, and active alerts for buses and trains.

Instructions

Public-transport punctuality now in a German region: share of trips >5 min late, skipped stops, cancellations, trend, alerts in force. Use when asked if buses and trains run normally, a strike, storm or works disrupt them, or for a line with no place ("ist die RB33 pünktlich?" → line: answered where it runs, or asks which region). Do NOT use for a station's departures or a line from a named DEPARTURE station ("RE1 ab Köln Hbf?"; "nach …" is no station) — get_train_departures. Figures are region-wide. Window ≤ 120 min. CC BY-SA (DELFI) or CC BY 4.0 (VBB, Berlin/Brandenburg): show attribution.

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": "check_transit_disruption"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNoLatitude in WGS 84, e.g. 48.137. Use with lon when the caller already holds coordinates; otherwise use region.
lonNoLongitude in WGS 84, e.g. 11.576. Use with lat; otherwise use region.
lineNoA line name as on the vehicle, e.g. "RB33", "S1", "RE 1", "U6". Give it when the question names a line; with no region the answer covers the Kreise the line runs through, or names the regions where lines of that name run. With region, it is that region's line of the name.
regionNoThe German region to report on, as free text: a Bundesland ("Bayern", "Bavaria", "Nordrhein-Westfalen"), a city ("Hamburg", "Köln"), a Kreis ("Landkreis Fulda") or one of the conurbations Ruhrgebiet, Rhein-Ruhr and Rhein-Main. A town inside a Kreis is reported as that Kreis and the answer says so, because the data is filed at Kreis level. Not a stop, not a street, not an address. Give either region OR lat+lon, never both.
languageNoSet this on every call to the language the person is writing in: "en" if they wrote English, "de" if they wrote German. Do not leave it out: it defaults to German ("de"), which is only the fallback when the language is genuinely unclear, so an English question sent without it is answered in German — a wrong answer. Place names, station names and road numbers are never translated in either language; in English the German term is kept in parentheses so the person recognises it on signs and in local apps.de
window_minNoHow many minutes back to look, 5–120 (default 60). The trend compares this window with the equally long one before it, so 60 means "the last hour against the hour before". Use a short window for "right now" and a long one for "has it been bad all morning".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.6.17
    • addedInput schema / properties / line
      Added value: +{
      +  "description": "A line name as on the vehicle, e.g. \"RB33\", \"S1\", \"RE 1\", \"U6\". Give it when the question names a line; with no region the answer covers the Kreise the line runs through, or names the regions where lines of that name run. With region, it is that region's line of the name.",
      +  "maxLength": 16,
      +  "minLength": 1,
      +  "type": "string"
      +}
  2. Changed1 schema field changedv2.1.18
    • changedInput schema / properties / language / description
      Previous value: -"Set this on every call to the language the person is writing in: \"en\" if they wrote English, \"de\" if they wrote German. Do not leave it out because it has a default — the default is only the fallback when the language is genuinely unclear, and an English question answered in German is a wrong answer. Place names, station names and road numbers are never translated in either language; in English the German term is kept in parentheses so the person recognises it on signs and in local apps."New value: +"Set this on every call to the language the person is writing in: \"en\" if they wrote English, \"de\" if they wrote German. Do not leave it out: it defaults to German (\"de\"), which is only the fallback when the language is genuinely unclear, so an English question sent without it is answered in German — a wrong answer. Place names, station names and road numbers are never translated in either language; in English the German term is kept in parentheses so the person recognises it on signs and in local apps."
  3. Changed2 schema fields changedv1.7.3
    • changedInput schema / properties / region / description
      Previous value: -"The German region to report on, as free text: a Bundesland (\"Bayern\", \"Bavaria\", \"Nordrhein-Westfalen\"), a city (\"Hamburg\", \"Köln\") or a Kreis (\"Landkreis Fulda\"). A town inside a Kreis is reported as that Kreis and the answer says so, because the data is filed at Kreis level. Not a stop, not a street, not an address. Give either region OR lat+lon, never both."New value: +"The German region to report on, as free text: a Bundesland (\"Bayern\", \"Bavaria\", \"Nordrhein-Westfalen\"), a city (\"Hamburg\", \"Köln\"), a Kreis (\"Landkreis Fulda\") or one of the conurbations Ruhrgebiet, Rhein-Ruhr and Rhein-Main. A town inside a Kreis is reported as that Kreis and the answer says so, because the data is filed at Kreis level. Not a stop, not a street, not an address. Give either region OR lat+lon, never both."
    • addedInput schema / properties / region / maxLength
      Added value: +120
  4. First observedv0.0.9

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds genuine context: figures are region-wide, the window is capped at 120 minutes, a town is reported as its Kreis because data is filed at Kreis level, and CC BY-SA / CC BY 4.0 attribution must be shown. What it does not disclose is anything about response shape or how sparse region-wide coverage can be, but for a read-only lookup that is a minor omission.

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?

Front-loaded with purpose, then usage, then exclusion, then licence — a sensible order with no filler sentences. It is dense to the point of being cryptic in places, notably the arrow notation in 'ist die RB33 pünktlich? → line: answered where it runs', and the window limit appears in both prose and schema.

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 six-parameter, all-optional, closed-world lookup with no output schema, the definition covers what the answer contains, how scope works (region-wide, Kreis-level filing), the admissible region forms, the line-without-region behaviour, and the licence obligation. Nothing an agent needs in order to call it correctly or report results 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 baseline is 3, and the description still adds real meaning: a line with no region is answered over the Kreise it runs through or by naming regions where that line exists, and region explicitly cannot be a stop, street or address. It repeats the 120-minute window cap already in the schema, which earns nothing.

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: public-transport punctuality in a German region, with the concrete metrics enumerated (share of trips >5 min late, skipped stops, cancellations, trend, alerts in force). It explicitly contrasts itself with get_train_departures, so an agent can tell the two apart without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives positive triggers (are buses/trains running normally, strike/storm/works, a line named with no place) and an explicit exclusion with a named alternative: station departures and "RE1 ab Köln Hbf" belong to get_train_departures. The parenthetical clarification that "nach …" is not a station removes a real ambiguity.

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