Skip to main content
Glama
OpenLMNP

OpenLMNP

Export Documents

export_documents
Read-only

Generates a ZIP of all invoices, receipts, and quotes organized by year and expense type, with optional year/type filters, and returns a temporary download URL.

Instructions

Génère un fichier ZIP contenant tous les justificatifs (factures, reçus, devis) de l'utilisateur, organisés par année et type (charges/mobilier/travaux). Filtrage optionnel par année et/ou type. Retourne une URL de téléchargement temporaire.

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": "export_documents"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoFiltrer par type : expense (charges), furniture (mobilier), work (travaux). Sans filtre : tous les types.
yearNoFiltrer par année (ex: 2025). Sans filtre : toutes les années.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.0.1
    • addedInput schema / properties / type / description
      Added value: +"Filtrer par type : expense (charges), furniture (mobilier), work (travaux). Sans filtre : tous les types."
    • addedInput schema / properties / year / description
      Added value: +"Filtrer par année (ex: 2025). Sans filtre : toutes les années."
  2. First observedv0.1.1

TDQS

A4/5.0
Behavior4/5

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

The readOnlyHint already tells the agent this does not mutate data, and the description adds genuinely new behavior: the output is a ZIP organized by year and type, and the call returns a temporary download URL. It stops short of stating how long that URL stays valid or whether large exports are rate-limited or truncated.

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?

Three short sentences, front-loaded with what is produced, then filtering, then the return value. No repetition of the title and no filler; every sentence adds information an agent needs.

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?

With no output schema, the description correctly fills the gap by describing the archive layout and the temporary URL return, and the two optional parameters are fully documented in the schema. What is missing is the lifetime of the URL and any size or scope limits, which matter for an export tool that can span all years.

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 coverage is 100% and both parameters already carry descriptions with example values, so the schema does the heavy lifting. The description only restates that filtering is optional by year and type and adds nothing about combined-filter behavior or format edge cases, matching the baseline of 3.

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 gives a specific verb and artifact ("Génère un fichier ZIP") plus the exact resource it contains ("tous les justificatifs (factures, reçus, devis)"), including how they are organized. This clearly separates it from sibling mutators such as create_expense or from other generators like generate_fec and generate_tax_return, which produce accounting files rather than a document archive.

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?

It states that filtering by year and/or type is optional and that unfiltered means all types and all years, which implies the retrieval use case. However, it never says when an agent should pick this over related tools (e.g., analyze_document for inspecting a single file, or generate_fec for accounting exports), and there are no explicit exclusions.

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