Skip to main content
Glama

RideMyPark

Parcourir la géographie RideMyPark

ridemypark_browse_geography
Read-onlyIdempotent

Parcourt l'arborescence géographique du catalogue public — pays, puis régions d'un pays, puis villes d'une région — avec le nombre de spots à chaque niveau.

Sert à répondre à « dans quels pays y a-t-il des spots ? », « quelles régions françaises sont les mieux couvertes ? », « quelles villes de Bretagne ont un skatepark ? ».

Paramètres :

  • country (string, 2 à 80 caractères) : slug du pays (« france »). Omis, l'outil rend la liste des pays.

  • region (string, 1 à 80 caractères) : slug de la région. Exige country ; l'outil rend alors les villes.

  • response_format ('markdown' | 'json') : défaut markdown.

Rend le niveau atteint (level), puis selon ce niveau :

  • countries : { country, country_slug, country_code, count } par pays ;

  • regions : country_slug, et { region, region_slug, count } par région (avec le pays de chacune) ;

  • cities : country_slug, region_slug, et { city, city_slug, count } par ville. Le slug à repasser au niveau suivant est country_slug, puis region_slug ; count est le nombre de fiches de la zone. country_code peut manquer.

Limites connues des données :

  • les compteurs portent sur les fiches GÉOCODÉES : une fiche sans coordonnées n'est comptée dans aucune zone ;

  • les slugs sont normalisés côté API (minuscules, sans accent) et ne correspondent pas toujours au nom d'usage ;

  • la couverture varie selon les pays et les villes.

Erreurs :

  • un slug inconnu ne lève PAS d'erreur : la liste revient vide. Reprendre un slug rendu au niveau précédent ;

  • region fourni sans country : l'outil refuse, car une région ne se résout pas sans son pays.

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": "ridemypark_browse_geography"
  }
}

Input Schema

NameRequiredDescriptionDefault
regionNoSlug de la région. Exige country ; rend alors les villes de cette région.
countryNoSlug du pays (« france », « united-states »). Omis : rend la liste des pays.
response_formatNomarkdown pour une réponse lisible, json pour les données brutes.markdown

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already establish read-only, idempotent, open-world, non-destructive behavior, and the description adds genuinely non-obvious traits: counters only cover geocoded records so uncoded spots vanish from every zone, slugs are API-normalized and may differ from display names, and coverage varies by country. The error section is especially valuable — an unknown slug returns an empty list rather than raising, and region without country is refused — which prevents an agent from misreading an empty result as 'no spots exist'.

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?

Purpose and example queries are front-loaded, then parameters, return shape, data limits, and errors are cleanly sectioned. It is longer than most tool descriptions, but nearly every block carries decision-relevant information; the return-shape enumeration is somewhat dense for a no-output-schema tool yet still earns its space.

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 must specify return values and does so per level (country/country_slug/country_code/count; region; city). Combined with full parameter documentation, the geocoding caveat, and the empty-list semantics, an agent has everything needed to call it and interpret results 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, but the description adds real meaning: the slug examples, the escalation contract ('Le slug à repasser au niveau suivant est country_slug, puis region_slug'), and the consequence of omission for each parameter. The region→country dependency is restated with its failure mode, going beyond the schema's bare 'Exige country'.

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 — walking the geographic tree (country → region → city) of the public catalog with spot counts at each level — and concretizes it with the exact questions it answers ("dans quels pays y a-t-il des spots ?", "quelles villes de Bretagne ont un skatepark ?"). An agent can tell this is a browse-by-geography tool, not a keyword search or single-area 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?

Gives clear usage context via the enumerated example questions and explains the drill-down protocol (omit country to list countries, add country to get regions, add region to get cities). It does not explicitly say when to prefer a sibling search tool or what this tool cannot answer, so no full when/when-not contrast.

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