Skip to main content
Glama
OpenLMNP

OpenLMNP

Create Expense

create_expense
Destructive

Record an operating expense for an LMNP rental property in euros, including date, category, amount, description, VAT, and optional recurrence or business-use details.

Instructions

Crée une charge d'exploitation pour un bien LMNP. Le montant est en euros. Catégories disponibles : property_tax, insurance, energy, maintenance, supplies, platform_fees, accounting, telecom, travel, cleaning, other.

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": {
      "property_id": "<property_id>",
      "expense_date": "<expense_date>",
      "amount": "<amount>",
      "category": "<category>",
      "description": "<description>"
    },
    "name": "create_expense"
  }
}

Input Schema

NameRequiredDescriptionDefault
notesNoNotes libres
amountYesMontant TTC en euros (ex: 250.00)
categoryYesCatégorie : property_tax, insurance, energy, maintenance, supplies, platform_fees, accounting, telecom, travel, cleaning, other
tva_rateNoTaux de TVA en pourcentage (ex: 20 pour 20%, 0 pour exonéré)
descriptionYesDescription de la charge
property_idYesIdentifiant du bien immobilier
expense_dateYesDate de la charge au format Y-m-d (ex: 2025-03-15)
is_dedicatedNoCharge 100% dédiée à la location (true) ou au prorata de la quote-part (false, défaut)
recurring_typeNoType de récurrence : once (défaut), monthly, quarterly, yearly
business_use_percentNoPart d'usage pour la location en pourcentage, pour une charge aussi personnelle (ex: 30 pour un forfait téléphone utilisé à 30 % pour la location). Absent = 100 %. S'applique avant la quote-part surface.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv2.0.1
    • addedInput schema / properties / amount / description
      Added value: +"Montant TTC en euros (ex: 250.00)"
    • addedInput schema / properties / business_use_percent
      Added value: +{
      +  "description": "Part d'usage pour la location en pourcentage, pour une charge aussi personnelle (ex: 30 pour un forfait téléphone utilisé à 30 % pour la location). Absent = 100 %. S'applique avant la quote-part surface.",
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • addedInput schema / properties / category / description
      Added value: +"Catégorie : property_tax, insurance, energy, maintenance, supplies, platform_fees, accounting, telecom, travel, cleaning, other"
    • addedInput schema / properties / description / description
      Added value: +"Description de la charge"
    • addedInput schema / properties / expense_date / description
      Added value: +"Date de la charge au format Y-m-d (ex: 2025-03-15)"
    • addedInput schema / properties / is_dedicated / description
      Added value: +"Charge 100% dédiée à la location (true) ou au prorata de la quote-part (false, défaut)"
    • addedInput schema / properties / notes / description
      Added value: +"Notes libres"
    • addedInput schema / properties / property_id / description
      Added value: +"Identifiant du bien immobilier"
    • addedInput schema / properties / recurring_type / description
      Added value: +"Type de récurrence : once (défaut), monthly, quarterly, yearly"
    • addedInput schema / properties / tva_rate / description
      Added value: +"Taux de TVA en pourcentage (ex: 20 pour 20%, 0 pour exonéré)"
  2. First observedv0.1.1

TDQS

B3.1/5.0
Behavior2/5

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

The only annotation is destructiveHint=true, so the description carries nearly the full behavioral burden. It says nothing about what happens on creation (returned identifier, validation failures), what recurring_type actually does (single record vs. generated schedule), or how is_dedicated and business_use_percent interact with fiscal calculations — the most consequential behaviors for a mutation in a tax tool.

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?

Three short sentences, front-loaded with purpose, with no filler. The category enumeration largely duplicates the schema's category description, which is minor redundancy rather than bloat.

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

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A 10-parameter mutation tool in a specialized French LMNP tax domain with no output schema needs more than this: the pro-rata semantics, recurrence behavior, and consequences for downstream depreciation/fiscal computations are absent. An agent could call it, but could easily create wrong-shaped data.

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 100% and every parameter is documented in the schema, so the baseline applies. The description restates the amount currency and the category list, both already in the schema, and adds no new meaning for is_dedicated, business_use_percent or recurring_type.

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?

"Crée une charge d'exploitation pour un bien LMNP" gives a specific verb plus resource and domain scope, which is enough to separate it from update_expense, delete_expense and the other create_* siblings. It stops short of explicitly contrasting with those siblings, so it lands just under the top mark.

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 agent can infer this is the tool for recording a new expense, but there is no statement of when to prefer it over update_expense, no prerequisites, and no guidance on how recurring or pro-rata expenses should be entered. Nothing misleading, but nothing that actively routes the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.