Skip to main content
Glama
OpenLMNP

OpenLMNP

Import Airbnb Csv

import_airbnb_csv
Destructive

Imports Airbnb transaction or reservation CSV data into a specified property, with optional preview, and returns counts of imported and skipped rows plus any errors.

Instructions

Importe un fichier CSV Airbnb (historique des transactions ou réservations) dans un bien donné. Le contenu du fichier CSV doit être encodé en base64 dans le champ csv_base64. Retourne le nombre de lignes importées, ignorées et les erreurs éventuelles.

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>",
      "csv_base64": "<csv_base64>"
    },
    "name": "import_airbnb_csv"
  }
}

Input Schema

NameRequiredDescriptionDefault
previewNoSi true, simule l'import sans enregistrer (affiche les 5 premières lignes)
csv_base64YesContenu du fichier CSV Airbnb encodé en base64
property_idYesID du bien dans lequel importer les revenus

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv2.0.1
    • addedInput schema / properties / csv_base64 / description
      Added value: +"Contenu du fichier CSV Airbnb encodé en base64"
    • addedInput schema / properties / preview / description
      Added value: +"Si true, simule l'import sans enregistrer (affiche les 5 premières lignes)"
    • addedInput schema / properties / property_id / description
      Added value: +"ID du bien dans lequel importer les revenus"
  2. First observedv0.1.1

TDQS

A3.5/5.0
Behavior3/5

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

The destructiveHint=true annotation already signals mutation, and the description usefully adds what the return contains (imported rows, skipped rows, errors) and the base64 encoding requirement. It does not disclose the consequences of destructiveness: whether existing transactions are overwritten or deduplicated, how skipped rows are determined, or whether the import is atomic on failure. For a destructive import tool that is a meaningful omission, but the return-value and encoding context is real added value.

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 compact sentences, front-loaded with purpose, then encoding requirement, then return shape. Every sentence carries information, though the base64 sentence partially duplicates the schema field description.

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?

With no output schema, the description properly explains the return counts and errors, and it is adequate for a 3-parameter tool. It falls short on the behavioral side: for a destructive import it should state what happens to pre-existing data and whether preview is the safe alternative for validation.

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 100%, so all three parameters are already documented, including preview's simulation behavior and first-five-rows output. The description reinforces the csv_base64 contract and the target property, adding light confirmation rather than new meaning, so it sits modestly above the baseline.

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 specific verb and resource: imports an Airbnb CSV (transaction history or reservations) into a given property. That is far more informative than the title. It does not, however, distinguish itself from sibling write tools like create_income or create_expense, which is the main clarity gap.

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 by the word 'importe' – an agent can infer bulk-loading of Airbnb data into a property. There is no explicit when-to-use guidance, no mention of alternatives (manual create_income/create_expense), and no stated prerequisites such as whether the property must exist or which CSV formats are accepted.

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