Skip to main content
Glama

TOISE — intelligence foncière

Étude de reconversion d’un bâtiment (que faire de ces bureaux vacants ?)

toise_etude_reconversion
Read-onlyIdempotent

Que faire de ces bureaux vacants (ou de ce bâtiment) : classement des usages de reconversion avec verdict PLU, complexité et coût, concurrents et enseignes autour. Entrée : adresse (ou lat/lon), caracteristiques et/ou teaser, poids. Base de travail subjective ; coûts à confirmer par devis. Valeur d'usage neuf : toise_potentiel_transformation.

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_etude_reconversion"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNo
lonNo
coutsNoAncien nom : équivaut à…
poidsNoPoids des axes…
teaserNoTexte d’un teaser collé : surface, R+n…
usagesNoRestreindre aux usages listés…
adresseNo
communeNo
sectionNo
rayon_kmNo
code_inseeNo
numero_parcelleNo
caracteristiquesNoCaractéristiques connues du bâtiment…
hypotheses_coutsNoVariables de coût modifiables…
hypotheses_valeurNoHypothèses de l’axe économique…

Output Schema

NameRequiredDescriptionDefault
pluNo
prixNo
liensNoLiens vers la fiche TOISE et vers des services de…
poidsYes
quotaNoQuota du jour après cet appel : { fonction, limite…
etapesNo
exclusYesUsages interdits par le PLU (avec citation).
annonceNoDonnées d’annonce lues : prix_eur, prix_qualificatif…
curseurNo
demandeNo
partielNo
sourcesYes
batimentNo
has_moreYes
rayon_kmNo
warningsYes
classementYesUsages classés : rang, score…
hypothesesNo
teaser_lusNo
contraintesNoContraintes du site…
localisationNo
quota_unitesNoUnités d’usage du jour : consommees_par_cet_appel…
avertissementYes
champs_absentsNoDonnées absentes du résultat partiel.
limite_atteinteNoPrésent quand un quota, une limite d’offre ou une fonction…
paiement_requisNoPrésent quand le résultat complet est un achat à l’acte…
hypotheses_coutsNovariables (cle, valeur, defaut, modifie, unite), modifiees…
hypotheses_valeurNovariables (cle, valeur, defaut), modifiees, valeurs_marche…
contradictions_teaserNoFaits cités avec des valeurs différentes…
origine_caracteristiquesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / couts / description
      Previous value: -"Ancien nom : équivaut à hypotheses_couts.bandes."New value: +"Ancien nom : équivaut à…"
    • changedInput schema / properties / poids / description
      Previous value: -"Poids des axes (défaut 25 chacun, normalisés)."New value: +"Poids des axes…"
    • changedInput schema / properties / usages / description
      Previous value: -"Restreindre aux usages listés (défaut : tous)."New value: +"Restreindre aux usages listés…"
  2. Changed1 schema field changed
    • changedInput schema / properties / teaser / description
      Previous value: -"Texte d’un teaser collé : surface, R+n, parking…"New value: +"Texte d’un teaser collé : surface, R+n…"
  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 readOnlyHint=true, destructiveHint=false, idempotentHint=true and openWorldHint=true, so safety and idempotency are covered. The description adds a genuinely useful caveat beyond the schema: the result is a subjective working basis and costs must be confirmed by quotes (devis). It does not discuss output confidence, data sources, or latency, so this is additive but not rich.

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 core purpose and entry modes are front-loaded in the first two sentences, and the caveat plus sibling pointer are compact trailing notes. It is dense and somewhat telegraphic, but no sentence is wasted.

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 annotations cover the safety profile. For a 15-parameter tool with deeply nested hypothesis objects, the description omits how those defaults and weight axes affect the result, so an agent could call it correctly but not knowingly tune it.

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 description does add meaning the schema cannot express: address or lat/lon are alternative entry modes, and caracteristiques and/or teaser are optional complements, plus 'poids' drives the ranking. However, with 47% schema coverage and 15 parameters including the substantial hypotheses_couts and hypotheses_valeur objects, it never mentions those cost/value assumption blocks or their defaults, leaving a significant portion undocumented in prose.

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 specific deliverable: ranking of reconversion uses with a PLU verdict, complexity, cost, and surrounding competitors/retail brands. It also names the sibling toise_potentiel_transformation as the tool for new-build use value, which helps differentiate. It is slightly rambling and mixes purpose with input hints, but an agent can tell what it produces.

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 clearly frames the trigger case ('que faire de ces bureaux vacants (ou de ce bâtiment)') and points to toise_potentiel_transformation for the adjacent new-build question. There is no explicit when-not guidance or prerequisite list, so it stops short of full routing 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