Skip to main content
Glama

fiscal_jeanbrun

Read-onlyIdempotent

Dispositif Jeanbrun (amortissement bailleur, LF 2026) — Nouveau dispositif d'amortissement du bailleur privé (LF 2026 art. 47, successeur de Pinel), fenêtre 21/02/2026 → 31/12/2028. Amortit 80 % du prix du logement au taux du couple logement (neuf / ancien rénové) × location (intermédiaire / social / très social), plafonné par an et par foyer, déductible du revenu foncier (IR à la TMI ; PS 17,2 % seulement jusqu'à annuler le revenu foncier net). Calcule l'amortissement annuel retenu et l'économie d'impôt (an, 9 ans = engagement minimal, 20 ans) ; l'amortissement n'a pas de durée maximale légale et court jusqu'à un cumul de 80 % du prix ; à la revente, les amortissements sont réintégrés à la plus-value (CGI 150 VB III). La TMI est fournie ou dérivée du revenu net imposable. ⚠️ BOFiP dédié attendu S2 2026 (calcul fondé sur le texte de loi). Version stateless. (sources: LF 2026 art. 47 (loi n° 2026-103 du 19/02/2026) ; CGI (amortissement bailleur — dispositif Jeanbrun) ; BOFiP dédié attendu S2 2026)

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": {
      "prix_logement": "<prix_logement>"
    },
    "name": "fiscal_jeanbrun"
  }
}

Input Schema

NameRequiredDescriptionDefault
partsNoParts de quotient familial (pour la TMI dérivée).
teaserNoAperçu gratuit, sans paiement : true renvoie le chiffre de tête avec sa confiance et ses sources (free preview, no payment).
situationNoSituation familiale (pour la TMI dérivée).Célibataire
prix_logementYesPrix du logement (€). L'assiette amortissable = 80 % (terrain forfait 20 %).
type_locationNoCatégorie de location (taux et plafond annuel croissants).Intermédiaire
type_logementNoNeuf ou ancien rénové (taux d'amortissement différents).Neuf
loyers_annuelsNoLoyers nus annuels du foyer, ce logement compris (€). Avec charges_annuelles et interets_annuels : économie RÉELLE (les PS ne baissent que jusqu'à annuler le revenu foncier net ; au-delà, déficit imputable plafonné à 10 700 €). Absent : maximum théorique, signalé dans hypothese_economie.
tmi_pourcentageNoTMI en points de % (ex. 30) si connue — court-circuite la dérivation depuis le revenu.
interets_annuelsNoIntérêts d'emprunt fonciers annuels du foyer (€).
charges_annuellesNoCharges foncières annuelles du foyer hors intérêts et hors amortissement (€).
revenu_net_imposableNoRevenu net imposable du foyer (€) — sert à dériver la TMI pour l'économie d'impôt. Ignoré si tmi_pourcentage fourni.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / teaser
      Added value: +{
      +  "default": false,
      +  "description": "Aperçu gratuit, sans paiement : true renvoie le chiffre de tête avec sa confiance et ses sources (free preview, no payment).",
      +  "type": "boolean"
      +}
  2. Changed3 schema fields changed
    • addedInput schema / properties / charges_annuelles
      Added value: +{
      +  "description": "Charges foncières annuelles du foyer hors intérêts et hors amortissement (€).",
      +  "minimum": 0,
      +  "type": "number"
      +}
    • addedInput schema / properties / interets_annuels
      Added value: +{
      +  "description": "Intérêts d'emprunt fonciers annuels du foyer (€).",
      +  "minimum": 0,
      +  "type": "number"
      +}
    • addedInput schema / properties / loyers_annuels
      Added value: +{
      +  "description": "Loyers nus annuels du foyer, ce logement compris (€). Avec charges_annuelles et interets_annuels : économie RÉELLE (les PS ne baissent que jusqu'à annuler le revenu foncier net ; au-delà, déficit imputable plafonné à 10 700 €). Absent : maximum théorique, signalé dans hypothese_economie.",
      +  "minimum": 0,
      +  "type": "number"
      +}
  3. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered; the description still adds real value by disclosing the stateless nature, the fact that the calculation rests on statutory text rather than a dedicated BOFiP expected S2 2026, and that amortissements are reintegrated into the capital-gains base on resale (CGI 150 VB III). These are behavioral and reliability caveats an agent could not obtain from the annotations. It stops short of describing error behavior or output shape.

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

Conciseness3/5

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

One dense paragraph mixing mechanics, legal citation, caveat and source list. The core action ('Calcule…') is buried mid-text rather than front-loaded, and the legal basis is repeated (LF 2026 art. 47 appears in both the body and the trailing sources), which costs room without adding 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?

For an 11-parameter, output-schema-less tax simulator this is quite complete: eligibility window, amortization mechanics, caps, deduction order against rental income, the 9-year commitment versus 20-year horizon, and the resale clawback are all stated. The omission is mainly that return fields are only obliquely implied ('amortissement annuel retenu et l'économie d'impôt'), which is tolerable given the absence of an output schema but leaves the response shape partly guesswork.

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 description coverage is 100%, so the baseline is 3, but the description genuinely deepens meaning: it explains that the amortizable base is 80% of price (20% deemed land), that the rate is a product of type_logement × type_location, and that TMI may be supplied directly or derived from net taxable income. That gives the enums and the TMI/income pair a coherent model rather than restating the schema.

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 specific resource (the Jeanbrun amortization scheme) and a specific computation: 'Calcule l'amortissement annuel retenu et l'économie d'impôt', plus the legal anchor (LF 2026 art. 47) and the eligibility window. It is unmistakable what the tool does. It does not, however, position itself against plausible siblings such as fiscal_foncier_regime or fiscal_lmnp_regime, so an agent must infer which rental tax simulator applies.

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?

Usage is only implied: the 'fenêtre 21/02/2026 → 31/12/2028' tells an agent when the regime applies, and 'La TMI est fournie ou dérivée du revenu net imposable' hints at input paths. There is no explicit statement of when to pick this tool over a sibling regime simulator, no exclusions, and no prerequisites (e.g. the property must be rented under a qualifying lease).

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.