Skip to main content
Glama

TOISE — intelligence foncière

Points d’intérêt autour d’un point

toise_points_interet
Read-onlyIdempotent

Quels commerces, écoles, transports et services autour d'une adresse (points d'intérêt dans un rayon). Rayon 50 à 2 000 m, OpenStreetMap (non exhaustif). Si SOURCE_INDISPONIBLE, une seule relance ; repli : toise_etablissements_naf, ou toise_mesures_terrain (mode autour) pour les transports.

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": "toise_points_interet"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNo
lonNo
limiteNo
adresseNo
curseurNo
rayon_mNo
categoriesNoCatégories demandées (toutes par défaut)…

Output Schema

NameRequiredDescriptionDefault
liensNoLiens vers la fiche TOISE et vers des services de…
listeYesPar catégorie : tableau de { osm, type, nom, distance_m }…
quotaNoQuota du jour après cet appel : { fonction, limite…
totalYesSomme des comptages ; null si OpenStreetMap est…
centreYes{ lat, lon, adresse_retenue }.
curseurYes
partielNotrue : une source n’a pas répondu, des champs manquent…
rayon_mYes
sourcesYes
comptageYesNombre réel d’éléments par catégorie…
has_moreYes
tourismeNoDATAtourisme dans le même rayon : comptage par catégorie…
visiteurNo
warningsYes
categoriesYes
vide_motifNo
total_exactYesFaux si le plafond de 500 objets d’Overpass est atteint.
interroge_leNoHorodatage de la base OSM lue.
quota_unitesNoUnités d’usage du jour : consommees_par_cet_appel…
champs_absentsNoDonnées absentes du résultat partiel.
osm_disponibleNoFaux si Overpass est en panne : réponse partielle…
limite_atteinteNoPrésent quand un quota, une limite d’offre ou une fonction…
paiement_requisNoPrésent quand le résultat complet est un achat à l’acte…
limite_appliqueeNo
erp_accessibiliteNoacceslibre : établissements recevant du public dans le même…

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedOutput schema / properties / osm_disponible
      Added value: +{
      +  "description": "Faux si Overpass est en panne : réponse partielle…",
      +  "type": "boolean"
      +}
    • changedOutput schema / properties / total / description
      Previous value: -"Somme des comptages."New value: +"Somme des comptages ; null si OpenStreetMap est…"
    • changedOutput schema / properties / total / type
      Previous value: -"number"New value: +[
      +  "number",
      +  "null"
      +]
  2. Changed2 schema fields changed
    • addedOutput schema / properties / erp_accessibilite
      Added value: +{
      +  "description": "acceslibre : établissements recevant du public dans le même…",
      +  "type": "object"
      +}
    • addedOutput schema / properties / tourisme
      Added value: +{
      +  "description": "DATAtourisme dans le même rayon : comptage par catégorie…",
      +  "type": "object"
      +}
  3. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds genuinely new behavioral context: the data source is OpenStreetMap and therefore non-exhaustive, and there is a defined retry-once policy with explicit fallbacks. Return volume, pagination behaviour and partial-result semantics are still not disclosed.

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?

Three compact sentences, front-loaded with purpose and radius limits, then source caveat, then the failure/fallback routing. No filler. The 'Si SOURCE_INDISPONIBLE' token is cryptic as written and slightly blurs an otherwise tight sentence.

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

Completeness3/5

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

With 7 parameters, 0 required, and an output schema present, the description covers purpose, scope, source caveat and fallbacks adequately. However, it leaves the input-selection question (coordinates vs address) and the pagination contract (limite/curseur) entirely to an input schema that is only 14% documented, which is a real gap for a tool an agent must invoke correctly on the first try.

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?

Schema description coverage is only 14% (essentially just the categories enum description), so the description must compensate. It does explain the radius bounds (50–2 000 m) and lists the default categories, but it says nothing about lat/lon versus adresse as alternative inputs, about limite (1–50) or about curseur for pagination — the two parameters an agent is most likely to mis-set.

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 names the concrete resource (commerces, écoles, transports, services autour d'une adresse / points d'intérêt dans un rayon) and the geographic scope, so an agent immediately knows it performs a proximity POI lookup. It does not use an explicit verb, and the question phrasing is slightly indirect, but the resource and radius scope are unambiguous.

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?

It gives an explicit error path ('Si SOURCE_INDISPONIBLE, une seule relance') and names concrete alternatives with their conditions: toise_etablissements_naf, or toise_mesures_terrain in 'mode autour' for transport. What is missing is when to use this versus other proximity tools such as toise_point or toise_dossier_adresse, and whether lat/lon or adresse should be preferred.

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