Skip to main content
Glama

assiette_sup

Retrieve public utility easement boundaries for specific geographic coordinates using France's Géoplateforme urban planning data.

Instructions

Renvoie les assiettes des servitudes d'utilité publique (SUP) pour une position donnée par sa longitude et sa latitude (source: Géoplateforme - (WFS Géoportail de l'Urbanisme)).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
lonYesLa longitude du point
latYesLa latitude du point

Implementation Reference

  • The AssietteSupTool class implements the 'assiette_sup' MCP tool, including its name, description, input schema, and the execute handler that delegates to getAssiettesServitudes helper.
    class AssietteSupTool extends MCPTool<SupInput> {
      name = "assiette_sup";
      description = `Renvoie les assiettes des servitudes d'utilité publique (SUP) pour une position donnée par sa longitude et sa latitude (source: ${URBANISME_SOURCE}).`;
    
      schema = {
        lon: {
          type: z.number(),
          description: "La longitude du point",
        },
        lat: {
          type: z.number(),
          description: "La latitude du point",
        },
      };
    
      async execute(input: SupInput) {
        logger.info(`assiette_sup(${input.lon},${input.lat})...`);
        return getAssiettesServitudes(input.lon, input.lat);
      }
    }
  • Input schema definition for the 'assiette_sup' tool using Zod for lon and lat validation.
    schema = {
      lon: {
        type: z.number(),
        description: "La longitude du point",
      },
      lat: {
        type: z.number(),
        description: "La latitude du point",
      },
    };
  • Core helper function getAssiettesServitudes that performs WFS query to Geoplateforme for SUP assiette features within 30 meters of the given (lon, lat) point.
    export async function getAssiettesServitudes(lon, lat) {
        logger.info(`getAssiettesServitudes(${lon},${lat})...`);
    
        // note that EPSG:4326 means lat,lon order for GeoServer -> flipped coordinates...
        const cql_filter = `DWITHIN(the_geom,Point(${lat} ${lon}),30,meters)`;
    
        const sourceGeom = {
            "type": "Point",
            "coordinates": [lon,lat]
        };
    
        // TODO : avoid useless geometry retrieval at WFS level
        const url = 'https://data.geopf.fr/wfs?' + new URLSearchParams({
            service: 'WFS',
            request: 'GetFeature',
            typeName: ASSIETTES_SUP_TYPES.join(','),
            outputFormat: 'application/json',
            cql_filter: cql_filter
        }).toString();
    
        const featureCollection = await fetchJSON(url);
        return featureCollection.features.map((feature) => {
            // parse type from id (ex: "commune.3837")
            const type = feature.id.split('.')[0];
            // ignore geometry and extend properties
            return Object.assign({
                type: type,
                id: feature.id,
                bbox: feature.bbox,
                distance: (distance(
                    sourceGeom,
                    feature.geometry
                ) * 1000.0)
            }, feature.properties);
        });
    }
  • Array of WFS type names used by the assiette_sup tool for querying SUP assiette layers (points, lines, surfaces).
    const ASSIETTES_SUP_TYPES = [
        'wfs_sup:assiette_sup_p',
        'wfs_sup:assiette_sup_l',
        'wfs_sup:assiette_sup_s',
    ];
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It states this is a read operation ('Renvoie') and mentions the data source, but doesn't cover important aspects like rate limits, authentication requirements, error conditions, response format, or whether this is a real-time query versus cached data. For a geographic data tool with zero annotation coverage, this leaves significant gaps.

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 description is appropriately concise - a single sentence that efficiently communicates the core functionality. It's front-loaded with the main purpose and includes the data source as helpful context. There's no wasted verbiage, though it could potentially benefit from slightly more structure for complex use cases.

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

Completeness2/5

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

Given that this is a geographic query tool with no annotations and no output schema, the description is incomplete. It doesn't explain what format the 'assiettes des servitudes d'utilité publique' data will be returned in, what specific information is included, whether there are limitations on coordinate systems, or how to interpret the results. The agent has insufficient information to properly use this tool.

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

Parameters3/5

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

The input schema has 100% description coverage, with both parameters ('lon' and 'lat') clearly documented in the schema. The description adds no additional parameter information beyond what's already in the schema. According to the scoring rules, when schema_description_coverage is high (>80%), the baseline is 3 even with no param info in the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Renvoie les assiettes des servitudes d'utilité publique (SUP) pour une position donnée par sa longitude et sa latitude.' It specifies the verb ('Renvoie' - returns), the resource ('assiettes des servitudes d'utilité publique'), and the input mechanism (longitude/latitude). However, it doesn't explicitly differentiate from sibling tools like 'urbanisme' or 'cadastre' that might also provide geographic data.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools, doesn't specify use cases or prerequisites, and offers no exclusion criteria. The agent must infer usage from the purpose alone.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ignfab/geocontext'

If you have feedback or need assistance with the MCP directory API, please join our Discord server