Skip to main content
Glama

TOISE — intelligence foncière

Établissements par code NAF autour d’un point

toise_etablissements_naf
Read-onlyIdempotent

Combien de concurrents (boulangeries, salles de sport…) autour d'un point : établissements actifs par code NAF, avec SIRET, enseigne et effectif. Entrée : lat, lon, naf (ex. 93.11Z), rayon_km. SIRENE ; aucun téléphone ni e-mail. Repli quand OpenStreetMap ne répond pas.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "lat": "<lat>",
      "lon": "<lon>",
      "naf": "<naf>"
    },
    "name": "toise_etablissements_naf"
  }
}

Input Schema

NameRequiredDescriptionDefault
latYes
lonYes
nafYesCode(s) NAF : complet (93.11Z, 9311Z) ou…
limiteNo
rayon_kmNo
effectif_maxNoEffectif salarié maximal.
effectif_minNoEffectif salarié minimal de l’établissement.
inclure_non_renseigneNoAvec un filtre d’effectif, garder aussi les…

Output Schema

NameRequiredDescriptionDefault
nafNo
liensNoLiens vers la fiche TOISE et vers des services de…
quotaNoQuota du jour après cet appel : { fonction, limite…
totalYesÉtablissements retenus dans la zone lue (avant limite).
centreNo
rendusNo
completNoFaux si l’annuaire n’a pas été lu entièrement : le total…
curseurNo
partielNotrue : une source n’a pas répondu, des champs manquent…
sourcesYes
has_moreYes
plafonneNo
rayon_kmNo
warningsYes
millesimeNo{ valeur:null, motif } : SIRENE est publié en continu…
quota_unitesNoUnités d’usage du jour : consommees_par_cet_appel…
champs_absentsNoDonnées absentes du résultat partiel.
etablissementsYes
limite_atteinteNoPrésent quand un quota, une limite d’offre ou une fonction…
paiement_requisNoPrésent quand le résultat complet est un achat à l’acte…

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / naf / description
      Previous value: -"Code(s) NAF : complet (93.11Z, 9311Z) ou début…"New value: +"Code(s) NAF : complet (93.11Z, 9311Z) ou…"
  2. Changed1 schema field changed
    • changedInput schema / properties / naf / description
      Previous value: -"Code(s) NAF : complet (93.11Z, 9311Z) ou début de…"New value: +"Code(s) NAF : complet (93.11Z, 9311Z) ou début…"
  3. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, open-world and non-destructive, so the safety bar is low; the description still adds substantive context: the data source is SIRENE, only active establishments are returned, and no phone/e-mail fields exist. The fallback behavior when OSM is unavailable is also 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?

Compact and front-loaded: the purpose and use case come first, then inputs, then source and exclusions. The telegraphic phrasing ('SIRENE ; aucun téléphone ni e-mail.') is efficient, though a bit clipped for a tool with eight parameters.

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?

An output schema exists, so explaining return format is unnecessary, and the source/coverage limits are stated. But for an 8-parameter geospatial query tool it omits guidance on the result cap (limite) and how the effectif filters combine with inclure_non_renseigne, which are the main correctness risks.

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?

With 50% schema description coverage across 8 parameters, the description covers 4 of them (lat, lon, naf with an example code, rayon_km) and hints that effectif is filterable. It says nothing about limite, effectif_min/effectif_max semantics, or inclure_non_renseigne, leaving real gaps that the schema only partly fills.

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 states a concrete operation: listing/counting active establishments by NAF code around a coordinate, with example use cases (bakeries, gyms) and returned fields (SIRET, enseigne, effectif). It is clearly distinct from analysis/verification siblings, though it never names the specific alternative it falls back from.

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

Usage Guidelines3/5

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

It gives one real usage condition — 'Repli quand OpenStreetMap ne répond pas' — which tells the agent this is a fallback when geo/POI lookup fails. However, it does not name the sibling tool that normally handles that case, nor state when this tool should NOT be used (e.g., for non-commercial/institutional lookups).

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