Skip to main content
Glama

Seoul Dataset

seoul_dataset
Read-onlyIdempotent

Generic passthrough to ANY Seoul Open Data Plaza service by its service name (서비스명), returns the raw rows. Use when a specific Seoul dataset is needed that the named tools don't cover (e.g. "CardSubwayStatsNew" subway ridership, "GetParkingInfo" parking, "tbCycleStationInfo" bike stations, "SPOP_LOCAL_RESD_DONG" population). Browse services at data.seoul.go.kr.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "end": 10,
      "start": 1,
      "service": "CardSubwayStatsNew"
    },
    "name": "seoul_dataset"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoEnd row (default 5; sample key caps at 5).
startNoStart row (1-based, default 1).
serviceYesSeoul Open Data service name, e.g. "GetParkingInfo", "tbCycleStationInfo".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, and the description adds the key behavioral fact that the response is raw, unshaped rows from an arbitrary upstream service. It does not mention authentication/API-key requirements or rate limits, which matter for a public-data passthrough, so it stops short of full disclosure.

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?

Front-loaded with the core purpose and return shape, then the selection rule, then a discovery pointer. Three sentences, no filler, and every clause adds information the agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description compensates by stating that raw rows come back. With only three params and full schema coverage, the remaining gap is operational detail (auth key, rate limits, unknown per-service row shape) rather than anything preventing a correct call.

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 an extra point by naming four real service identifiers (CardSubwayStatsNew, GetParkingInfo, tbCycleStationInfo, SPOP_LOCAL_RESD_DONG) and the Korean term 서비스명, which tells the agent what a valid service value looks like beyond the two schema examples.

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 mechanism and resource: a generic passthrough to any Seoul Open Data Plaza service by service name, returning raw rows. It explicitly distinguishes itself from the named Seoul tools (seoul_air_quality, seoul_events, seoul_real_estate) by positioning itself as the fallback when a specific dataset is not covered.

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 an explicit trigger ('use when a specific Seoul dataset is needed that the named tools don't cover') plus the inverse condition implied by that clause, and points the agent to data.seoul.go.kr to discover valid service names. Concrete example datasets show what 'covered elsewhere' looks like in practice.

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.