Skip to main content
Glama

TOISE — intelligence foncière

Exporter un résultat en Word, CSV ou JSON (lien signé)

toise_export

Obtenir un mémo, un dossier ou une étude en Word, ou un tableau en CSV / JSON, à imprimer ou envoyer : CRÉE UN FICHIER, rendu par lien de téléchargement signé et enregistré dans Mon espace pour les offres payantes. Lien signé à durée limitée. Entrée : outil + arguments (ré-exécuté) ou donnees ; document memo_second_avis, dossier ou etude en .docx.

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": "toise_export"
  }
}

Input Schema

NameRequiredDescriptionDefault
nomNoNom du fichier sans extension…
outilNoOutil de lecture à ré-exécuter côté serveur…
titreNoAvec docx dossier ou etude : titre du document…
formatNocsv…
adresseNo
donneesNoLignes (objets) déjà obtenues d’un outil…
documentNoAvec format docx : memo_second_avis…
argumentsNoArguments de cet outil…
cle_tableauNoChemin pointé du tableau à exporter dans le…
duree_minutesNoValidité du lien : 15 à 1440 minutes…
prix_demande_eurNo
max_telechargementsNoNombre de téléchargements autorisés (défaut 3).

Output Schema

NameRequiredDescriptionDefault
urlYesLien de téléchargement signé (secret porteur).
liensNoLiens vers la fiche TOISE et vers des services de…
quotaNoQuota du jour après cet appel : { fonction, limite…
formatNo
lignesNo
sha256Yes
curseurNo
partielNotrue : une source n’a pas répondu, des champs manquent…
sourcesYes
colonnesNo
has_moreYes
warningsYes
expire_leYesDate-heure ISO d’expiration du lien.
provenanceNorecalcule_cote_serveur | fournies_par_le_client.
nom_fichierNo
outil_sourceNo
quota_unitesNoUnités d’usage du jour : consommees_par_cet_appel…
avertissementNo
taille_octetsYes
champs_absentsNoDonnées absentes du résultat partiel.
limite_atteinteNoPrésent quand un quota, une limite d’offre ou une fonction…
paiement_requisNoPrésent quand le résultat complet est un achat à l’acte…
valeurs_masqueesNo
colonnes_retireesNoColonnes sensibles retirées de l’export.
max_telechargementsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / duree_minutes / description
      Previous value: -"Validité du lien : 15 à 1440 minutes (défaut 15)."New value: +"Validité du lien : 15 à 1440 minutes…"
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false), it discloses the genuinely important behaviors: a file is created, returned as a time-limited signed download link, and stored in "Mon espace" only for paid plans, and that the source tool is re-executed. It does not cover overwrite behavior when nom collides, quotas, or download-count semantics, leaving some mutation risk opaque.

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?

One dense paragraph that front-loads the output (what you receive) before the mechanics, with the caps emphasis drawing the eye to the file-creation trait. It is a run-on chain of colons and semicolons, so a little restructuring would improve scanning, but no sentence is filler.

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 a 12-parameter, nested-object tool with an output schema (so return values needn't be explained), the description covers the input modes, formats, link lifetime and storage side effect. Gaps remain around the pricing/download-limit parameters and file-naming collisions, which the schema names but does not explain.

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 already 83%, so the baseline is 3, but the description adds real meaning the schema cannot: the relationship between outil/arguments (re-run) versus donnees (pre-fetched rows), and the coupling of document with .docx. Remaining parameters such as prix_demande_eur, max_telechargements, cle_tableau and adresse are left entirely to the schema.

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 names a concrete verb (produire/créer un fichier) and enumerates the exact resources and formats: mémo, dossier, étude en Word, tableau en CSV/JSON. The emphasized "CRÉE UN FICHIER" immediately separates it from the sibling read-only tools (toise_dvf_historique, toise_dossier_adresse, etc.), so an agent can tell what it produces without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the two accepted input paths — either point to a read tool plus its arguments (re-executed server-side) or pass already-obtained donnees — which is exactly the decision an agent must make before calling. It also gives the intent ("à imprimer ou envoyer") but offers no explicit exclusions or advice on when export is unnecessary.

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.

Resources