Skip to main content
Glama

TOISE — intelligence foncière

Bilan d’exploitation hôtelière : EBITDA, RevPAR, valorisation

toise_bilan_exploitation
Read-onlyIdempotent

Un hôtel ou un restaurant est-il rentable sur UNE année : compte d'exploitation USALI (RevPAR, GOP, EBITDA) et valorisation sur l'EBITDA. Avec code_insee : offre hôtelière et taxe de séjour. BP sur dix ans d'un investisseur : toise_bp_exploitation. Ne pas combiner les deux sans expliquer l'écart d'hypothèses. Ratios par défaut = hypothèses.

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_bilan_exploitation"
  }
}

Input Schema

NameRequiredDescriptionDefault
zoneNoRatios de référence parisiens.
choixNoHypothèses de financement et de sortie…
joursNoDéfaut 365.
ebitdaNo
ratiosNoRatios de charges imposés…
etoilesNo0 = non classé.
loyer_anNo
code_inseeNo
ebitda_pctNo
ffe_pct_caNoDéfaut 4 % du CA.
nb_chambresNo
loyer_estimeNo
personnel_anNo
prix_moyen_htNo
chiffre_affairesNo
duree_credit_ansNoAmortissement 1/durée.
prix_acquisitionNoMurs et/ou fonds, € (alias prix_terrain).
ca_restauration_htNoRestauration/bar HT, €.
taux_occupation_pctNo
taux_capitalisation_pctNoValeur = EBITDA ÷ taux.

Output Schema

NameRequiredDescriptionDefault
liensNoLiens vers la fiche TOISE et vers des services de…
quotaNoQuota du jour après cet appel : { fonction, limite…
ebitdaYes
curseurNo
partielNotrue : une source n’a pas répondu, des champs manquent…
sourcesYes
activiteYeschambres, taux_occupation_pct, nuitees, prix_moyen_ht…
has_moreYes
warningsYes
quota_unitesNoUnités d’usage du jour : consommees_par_cet_appel…
valorisationYesSur EBITDA : prix_acquisition, rendement_initial_pct…
avertissementNo
champs_absentsNoDonnées absentes du résultat partiel.
ignored_inputsYesClés de choix ou de ratios reçues mais sans effet…
motifs_absenceYesPour chaque champ null, le motif.
limite_atteinteNoPrésent quand un quota, une limite d’offre ou une fonction…
paiement_requisNoPrésent quand le résultat complet est un achat à l’acte…
ratios_referenceYesRatios de charges de référence, étiquetés HYPOTHÈSES…
financement_retenuNoAvec prix_acquisition : ltv_pct, taux_pct…
compte_exploitationYesproduits, charges_exploitation (postes et assiettes)…
contexte_concurrentielNoAvec code_insee : capacite…
sensibilite_occupationNoGOP à moins dix points d’occupation et charges qui ne…
estimation_loyer_commercialNoAvec loyer_estime : fourchette bas/médian/haut € HT…

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changed
    • changedInput schema / properties / ca_restauration_ht / description
      Previous value: -"Chiffre d’affaires annuel de restauration/bar…"New value: +"Restauration/bar HT, €."
    • changedInput schema / properties / duree_credit_ans / description
      Previous value: -"Durée du crédit en années : fixe…"New value: +"Amortissement 1/durée."
    • changedInput schema / properties / ffe_pct_ca / description
      Previous value: -"Réserve FF&E en % du chiffre d’affaires…"New value: +"Défaut 4 % du CA."
    • changedInput schema / properties / jours / description
      Previous value: -"Jours d’ouverture (365 par défaut)."New value: +"Défaut 365."
    • addedInput schema / properties / loyer_estime
      Added value: +{
      +  "type": "object"
      +}
    • changedInput schema / properties / prix_acquisition / description
      Previous value: -"Prix d’acquisition (murs, fonds ou les deux)…"New value: +"Murs et/ou fonds, € (alias prix_terrain)."
    • changedInput schema / properties / taux_capitalisation_pct / description
      Previous value: -"Taux de capitalisation visé, en % : valeur…"New value: +"Valeur = EBITDA ÷ taux."
    • changedInput schema / properties / zone / description
      Previous value: -"Localisation de l’hôtel : Paris, grandes…"New value: +"Ratios de référence parisiens."
    • addedOutput schema / properties / estimation_loyer_commercial
      Added value: +{
      +  "description": "Avec loyer_estime : fourchette bas/médian/haut € HT…",
      +  "type": [
      +    "object",
      +    "null"
      +  ]
      +}
  2. Changed6 schema fields changed
    • changedInput schema / properties / ca_restauration_ht / description
      Previous value: -"Chiffre d’affaires annuel de restauration/bar HT…"New value: +"Chiffre d’affaires annuel de restauration/bar…"
    • addedInput schema / properties / code_insee
      Added value: +{
      +  "type": "string"
      +}
    • changedInput schema / properties / duree_credit_ans / description
      Previous value: -"Durée du crédit en années : fixe l’amortissement…"New value: +"Durée du crédit en années : fixe…"
    • addedInput schema / properties / etoiles
      Added value: +{
      +  "description": "0 = non classé.",
      +  "maximum": 5,
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • changedInput schema / properties / prix_acquisition / description
      Previous value: -"Prix d’acquisition (murs, fonds ou les deux), en…"New value: +"Prix d’acquisition (murs, fonds ou les deux)…"
    • addedOutput schema / properties / contexte_concurrentiel
      Added value: +{
      +  "description": "Avec code_insee : capacite…",
      +  "type": [
      +    "object",
      +    "null"
      +  ]
      +}
  3. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint false), so the description doesn't need to. What it does add is substantive: default ratios are hypotheses rather than observed data, and code_insee changes the returned content — both directly affect how an agent should present results. It stops short of describing modelling assumptions or output reliability limits.

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?

Four short, dense sentences with the purpose first, then the code_insee branch, then the alternative and the anti-pattern warning. There is no filler, and every clause carries decision-relevant information.

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

Completeness4/5

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 description covers purpose, scoping, alternative routing and the key caveat about default hypotheses. For a 20-parameter valuation model it could do more on the financing/exit hypothesis object, but nothing required to invoke it correctly is missing.

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 20 parameters, nested objects (choix, ratios, loyer_estime) and only 50% schema description coverage, the schema leaves real gaps. The description compensates for a few: code_insee's effect on outputs and the fact that default ratios are hypotheses. It says nothing about choix (hypothèses de financement/sortie), loyer_estime, or how ebitda/ebitda_pct interact, so many parameters remain defined only by name.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource (compte d'exploitation USALI) and the concrete outputs (RevPAR, GOP, EBITDA, valorisation sur l'EBITDA) for a bounded scope (UNE année, hôtel ou restaurant). It goes further by contrasting with the named sibling toise_bp_exploitation (dix ans, investisseur), so an agent can route without opening either schema.

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

Usage Guidelines5/5

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

States the selecting condition (single-year profitability vs a ten-year business plan), names the alternative toise_bp_exploitation explicitly, and adds a real usage rule: 'Ne pas combiner les deux sans expliquer l'écart d'hypothèses.' It also tells the agent that supplying code_insee switches on extra outputs (offre hôtelière, taxe de séjour).

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