Skip to main content
Glama
OpenLMNP

OpenLMNP

Generate Fec

generate_fec
Idempotent

Generate the French FEC accounting export for a given fiscal year, producing the regulatory 18-column TAB-separated file required for tax audits. Specify the year to compute and download it.

Instructions

Génère le Fichier des Écritures Comptables (FEC) pour un exercice fiscal. Le FEC est un fichier réglementaire au format normé (article A.47 A-1 du LPF, 18 colonnes, séparateur TAB) requis en cas de contrôle fiscal. L'exercice est calculé avant la génération si nécessaire. Le fichier n'est pas conservé sur le serveur : il se télécharge depuis la page Exercices fiscaux.

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": {
      "year": "<year>"
    },
    "name": "generate_fec"
  }
}

Input Schema

NameRequiredDescriptionDefault
yearYesAnnée fiscale pour laquelle générer le FEC (ex : 2025)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.0.1
    • addedInput schema / properties / year / description
      Added value: +"Année fiscale pour laquelle générer le FEC (ex : 2025)"
  2. First observedv0.1.1

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior: the fiscal exercise is computed before generation if needed, and the file is not persisted server-side but retrieved via the Exercices fiscaux page. It stops short of stating permissions or what happens on a missing/incomplete exercise.

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 sentences, front-loaded with the action, then format specification, then year computation, then the delivery mechanism. Every sentence adds information the agent cannot get from the schema or annotations; nothing is redundant.

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

Completeness5/5

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

For a one-parameter, non-destructive generation tool with no output schema, the description covers what is produced, its regulatory format, prerequisite computation, and where the result is retrieved. Since no file is returned server-side, the download instruction effectively substitutes for missing return-value documentation.

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 the single `year` parameter is fully documented in the schema (integer, example 2025). The description adds only the indirect note that the exercise is calculated before generation, which hints at how the year is resolved but gives no detail on validation or failure for a non-existent exercise. Baseline 3 is appropriate.

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 verb and artifact ('Génère le Fichier des Écritures Comptables') and defines what the FEC is (regulatory file, article A.47 A-1 du LPF, 18 columns, TAB separator). An agent knows exactly what will be produced. It does not explicitly distinguish itself from the sibling generate_tax_return, which keeps it at 4 rather than 5.

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?

'Requis en cas de contrôle fiscal' implies the usage context, and the statement that the file must be downloaded from the Exercices fiscaux page tells the agent what to do next. However, there is no explicit when-to-use/when-not-to-use guidance or any contrast with the other generation tools in the catalog.

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