Skip to main content
Glama

TOISE — intelligence foncière

Points du client : import, rattachement aux zones, sites similaires

toise_reseau_client
Destructive

Mon réseau : mes points privés (CSV d'adresses) rattachés aux zones, et les IRIS ou communes qui ressemblent à mes meilleurs sites. Actions importer (BAN), lister, supprimer un lot, rattacher (format toise_zone_chalandise), similaires (7 indicateurs INSEE, écarts expliqués), zones_blanches (communes loin du réseau). Compte requis.

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": {
      "action": "<action>"
    },
    "name": "toise_reseau_client"
  }
}

Input Schema

NameRequiredDescriptionDefault
csvNoColonne adresse ; libelle, cp, ville…
lotNo
modeNo
zonesNo
actionYes
limiteNo
niveauNo
minutesNo
referencesNoAdresses des sites (défaut : le lot).
departementsNo
population_minNo

Output Schema

NameRequiredDescriptionDefault
okYes
lotNo
liensNoLiens vers la fiche TOISE et vers des services de…
quotaNoQuota du jour après cet appel : { fonction, limite…
actionYes
importNoBilan d’import : géocodés, douteux, introuvables, à…
pointsNo
partielNotrue : une source n’a pas répondu, des champs manquent…
sourcesNoProvenance : nom, licence, millésime de chaque source.
has_moreNo
warningsNo
similairesNoProfil de référence, candidats classés avec similarité…
quota_unitesNoUnités d’usage du jour : consommees_par_cet_appel…
rattachementNoPoints par zone, hors zones, multi-zones.
champs_absentsNoDonnées absentes du résultat partiel.
zones_blanchesNoCommunes à potentiel sans point du réseau à moins de X min…
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. Changed6 schema fields changed
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "importer",
      -  "lister",
      -  "rattacher",
      -  "similaires",
      -  "supprimer"
      -]New value: +[
      +  "importer",
      +  "lister",
      +  "rattacher",
      +  "similaires",
      +  "supprimer",
      +  "zones_blanches"
      +]
    • changedInput schema / properties / csv / description
      Previous value: -"Colonne adresse ; libelle, cp, ville facultatifs."New value: +"Colonne adresse ; libelle, cp, ville…"
    • addedInput schema / properties / minutes
      Added value: +{
      +  "type": "number"
      +}
    • addedInput schema / properties / mode
      Added value: +{
      +  "enum": [
      +    "voiture",
      +    "a_pied"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / population_min
      Added value: +{
      +  "type": "number"
      +}
    • addedOutput schema / properties / zones_blanches
      Added value: +{
      +  "description": "Communes à potentiel sans point du réseau à moins de X min…",
      +  "type": [
      +    "object",
      +    "null"
      +  ]
      +}
  2. First observed

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, so the safety profile is known; the description's 'supprimer un lot' and 'Compte requis' are consistent additions and the auth prerequisite is genuine extra information. It does not say whether batch deletion is reversible, what exactly is removed, or any CSV size or rate constraints for imports. Useful, but not rich behavioral context.

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 purpose statement is front-loaded ahead of the action list, and every clause carries information with no filler. The telegraphic parenthetical style packs a lot in, though the density and heavy parenthesization make it slightly harder to scan as a routing decision aid.

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 return values need no explanation, and the account requirement plus action inventory cover the basics for a six-action destructive tool. What is missing is the mapping from parameters to actions and any warning about the destructive delete path, which matters given 11 parameters at low schema coverage. Adequate but with clear gaps.

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 18% across 11 parameters, so the description must carry weight; it partially does by tying actions to inputs (CSV of addresses, a lot to delete, toise_zone_chalandise format for zones, IRIS vs commune level). It leaves several parameters unexplained, notably mode (voiture/a_pied), minutes, departements and population_min, which likely scope the zones_blanches and similaires computations. Partial compensation for a large coverage gap.

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 a concrete resource and scope: private client points from an address CSV attached to zones, plus IRIS/communes resembling the user's best sites, and it enumerates the six supported actions. The phrase 'mes points privés' implicitly separates it from a brand-wide network tool, but no sibling is explicitly named as a contrast. Purpose is clear; differentiation from toise_reseau_enseigne is left to inference.

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?

Each action carries a short gloss ('importer (BAN)', 'rattacher (format toise_zone_chalandise)', 'zones_blanches (communes loin du réseau)'), which gives implied per-action context. However there is no statement of when this tool should be preferred over siblings such as toise_zone_chalandise or toise_reseau_enseigne, and no exclusions or prerequisites beyond 'Compte requis'. Usage is inferable but not spelled out.

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