Japan Toilet & Accessibility

get_toilet_by_station

Read-onlyIdempotent

Look up wheelchair-accessible / multipurpose toilets inside a train station, including floor, gender, equipment (wheelchair, ostomate, diaper table) and the nearest exit. Covers 526 Tokyo stations (Tokyo Bureau of Social Welfare data). Major stations outside Tokyo (Yokohama, Kawasaki, Omiya, Chiba, Fujisawa, Shin-Yokohama…) return an in-station layer that groups accessible toilets by ticket gate — inside vs outside — per railway operator. Accepts Japanese (新宿, 横浜) or romaji (Shinjuku, Yokohama) for major stations.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`station`	Yes	Station name in Japanese (新宿, 渋谷) or romaji for major stations (Shinjuku, Shibuya, Kita-Senju).

Output Schema

TableJSON Schema

Name	Required	Description
`note`	No	Human-readable note.
`count`	No	Toilets returned.
`error`	No	Set when nothing was found.
`layer`	No	Data layer (e.g. in_station_gate).
`source`	No	Data source label.
`station`	No	Resolved station (English).
`toilets`	No	Accessible toilets with floor, gender, equipment and nearest exit.
`station_ja`	No	Station name in Japanese.
`attribution`	No	Data source(s), license and provenance — an object, or an array of sources.
`station_name_source`	No	How the name was resolved.

TDQS

A4.6/5.0

Behavior4/5

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

Annotations declare readOnlyHint=true and idempotentHint=true; the description adds behavioral context: data source, coverage limits, and grouping by ticket gate for major stations. No contradictions, and description adds value beyond 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 three sentences, each adding essential information: purpose and attributes, coverage details, input format and special behavior. No redundancy or filler; well front-loaded.

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?

The description covers all necessary context: data source, geographic scope, input variations, and special behavior for major stations. An output schema exists, so return values need not be explained. Complete for this tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single 'station' parameter is described in the schema with basic input guidance. The description significantly enhances this by providing examples (新宿, Shinjuku), clarifying that major stations outside Tokyo return a grouped layer, and noting that romaji works only for major stations.

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 clearly states the tool looks up wheelchair-accessible toilets in train stations with specific attributes (floor, gender, equipment, nearest exit) and coverage (526 Tokyo stations, major stations outside Tokyo). It distinguishes from sibling 'get_public_toilet_by_city' by focusing on station-specific toilets.

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 provides clear context for when to use the tool (looking up station toilets) and specifies input formats (Japanese or romaji). It does not explicitly exclude cases or mention alternatives, but the context is sufficient for an agent to infer usage.

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

All Japan Toilet & Accessibility tools Inspect

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

A4.1/5.0

Disambiguation2/5

Several tools have overlapping purposes: get_active_alerts and get_station_alerts both return JMA flood/landslide alerts, differing only by input type. Similarly, get_municipality_context and get_station_context expose the same underlying data via different resolvers, and get_station_context already includes hazard categories that get_station_hazard duplicates in more detail. These overlaps make it difficult for an agent to know which tool to select for a given query.

Naming Consistency4/5

Most tools follow a clear 'get_' prefix (e.g., get_toilet_by_station, get_train_status), which is consistent. However, 'station_search' and 'ping' break the pattern, and the role-split text references a non-existent 'search_ramen' tool. The dominant convention is clear, but the exceptions introduce minor inconsistency.

Tool Count4/5

With 10 tools, the count is within a reasonable range for the server's broad scope (station info, toilet accessibility, hazards, alerts, train status). However, the redundancy between municipality_context/station_context and actives_alerts/station_alerts means not every tool earns a unique place, making the set slightly over-provisioned. Still, it is not excessively large.

Completeness3/5

The server covers the main info-retrieval needs for toilets, station hazards, alerts, and train status. However, station_search explicitly tells agents to 'search_ramen' for ramen details, yet that tool is not provided, creating a clear dead end. Also, the domain is broader than the server name suggests, and some peripheral data (e.g., detailed ramen profiles) is only partially surfaced.

Resources

Need Help?