Skip to main content
Glama

TOISE — intelligence foncière

Scénarios d'usage d'un terrain, prix maximal admissible et verdict

toise_scenarios_usage
Read-onlyIdempotent

Bureaux, logement, commerce, logistique ou hôtel : quel programme peut payer le mieux le foncier sur ce terrain. Entrée : surface_plancher_m2 (+ prix_demande ; code_insee et section pour caler le logement sur DVF). Aide à la décision, pas un conseil.

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": {
      "surface_plancher_m2": "<surface_plancher_m2>"
    },
    "name": "toise_scenarios_usage"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoDéfaut terrain. batiment_existant…
zoneNoZone du PLU…
choixNoSubstitutions par programme, ex. {…
sectionNo
code_inseeNo
destinationsNoChamp `destinations` rendu par…
prix_demandeNoPrix demandé du terrain, en euros, pour…
ecart_rendement_bpsNoÉcart de rendement exigé sur coût pour les…
marge_promoteur_pctNoMarge du promoteur pour les programmes de…
surface_plancher_m2Yes

Output Schema

NameRequiredDescriptionDefault
modeNoterrain ou batiment_existant.
zoneNo
liensNoLiens vers la fiche TOISE et vers des services de…
quotaNoQuota du jour après cet appel : { fonction, limite…
totalYesNombre réel de scénarios chiffrés.
curseurNo
partielNotrue : une source n’a pas répondu, des champs manquent…
sourcesYes
verdictYesConstat mesuré…
has_moreYes
syntheseNoraisons et points à vérifier.
warningsYes
millesimeNo
scenariosYesProgrammes classés par prix maximal admissible décroissant…
ecartes_pluNoAvec destinations : programmes dont la sous-destination est…
hors_grilleNo
piste_auditYesUne ligne par valeur du calcul : poste, valeur, unite…
base_surfaceNoEn mode batiment_existant : la surface retenue est la…
quota_unitesNoUnités d’usage du jour : consommees_par_cet_appel…
avertissementNo
champs_absentsNoDonnées absentes du résultat partiel.
ignored_inputsNoClés de choix reçues mais sans effet (programme.cle)…
meilleur_usageNo
motifs_absenceNo
limite_atteinteNoPrésent quand un quota, une limite d’offre ou une fonction…
marche_logementNoCalage DVF : { ok, prix_m2, echantillon, fourchette } ou {…
paiement_requisNoPrésent quand le résultat complet est un achat à l’acte…
piste_audit_csvNoLa même table en CSV (séparateur point-virgule).
surface_plancher_m2Yes
prix_max_admissible_eurNoPrix maximal admissible du meilleur usage.
constructibilite_theoriqueNoEn mode batiment_existant : { applicable: false, motif }.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / choix / description
      Previous value: -"Substitutions par programme, ex. { \"bureaux\": {…"New value: +"Substitutions par programme, ex. {…"
    • changedInput schema / properties / prix_demande / description
      Previous value: -"Prix demandé du terrain, en euros, pour rendre…"New value: +"Prix demandé du terrain, en euros, pour…"
  2. Changed3 schema fields changed
    • changedInput schema / properties / marge_promoteur_pct / description
      Previous value: -"Marge du promoteur pour les programmes de vente…"New value: +"Marge du promoteur pour les programmes de…"
    • changedInput schema / properties / prix_demande / description
      Previous value: -"Prix demandé du terrain, en euros, pour rendre le…"New value: +"Prix demandé du terrain, en euros, pour rendre…"
    • changedInput schema / properties / zone / description
      Previous value: -"Zone du PLU (recopiée, sans effet sur le calcul)."New value: +"Zone du PLU…"
  3. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so safety is covered. The description adds genuinely useful context: housing calibration depends on DVF via code_insee/section, and results are decision support rather than advice. It says nothing about what the computation returns or its sensitivity to the tuning parameters, which matters for a 10-parameter simulation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences: the question and program list come first, the required and optional inputs second, the caveat last. No filler and nothing buried.

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 not be described, and the core required input is named. But for a tool with 10 parameters, enum/nested-object inputs and two operating modes, the description omits how the sensitivity levers change the verdict, leaving the agent without enough to call it confidently beyond the minimum.

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 70%, so the baseline is 3, but the description adds meaning for two parameters the schema leaves bare (section, code_insee) by explaining they are used to anchor housing values on DVF, and it frames prix_demande as the optional comparison price. It still says nothing about mode, zone, choix, destinations, ecart_rendement_bps or marge_promoteur_pct, which leaves the four tuning levers unexplained.

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?

States a concrete analytic outcome — which program (offices, housing, retail, logistics, hotel) can best pay for the land — plus the required input. That is a specific verb-plus-resource purpose, though it relies on the title/name to signal that the output is a max admissible price and verdict rather than naming it in the description body.

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?

'Entrée : surface_plancher_m2 (+ prix_demande ; code_insee et section...)' gives the entry conditions implicitly, so an agent can infer this is for pre-acquisition program/valorisation screening. However, no when-not conditions and no named alternative among the many siblings (e.g. bilan_operation, etude_marche) are offered, so the choice between tools is left to inference. The closing 'Aide à la décision, pas un conseil' is a disclaimer, not usage guidance.

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