Skip to main content
Glama

TOISE — intelligence foncière

Vérifier un teaser face aux données indépendantes TOISE

toise_deal_verify
Read-onlyIdempotent

Vérifier un teaser ou une dataroom collé en texte (prix, propriétaire, permis, potentiel, risques) : un verdict par affirmation. Une fourchette n'est jamais une erreur. Extraction seule des chiffres : toise_teaser.

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": {
      "texte": "<texte>"
    },
    "name": "toise_deal_verify"
  }
}

Input Schema

NameRequiredDescriptionDefault
texteYesTexte du teaser ou de la dataroom collé…
adresseNo

Output Schema

NameRequiredDescriptionDefault
liensNoLiens vers la fiche TOISE et vers des services de…
quotaNoQuota du jour après cet appel : { fonction, limite…
curseurNo
partielNotrue : une source n’a pas répondu, des champs manquent…
sourcesYes
confirmeYesAffirmations confirmées par une source TOISE indépendante.
has_moreYes
warningsYes
manquantsYesChamps financiers (prix, loyer, surface, rendement) que le…
enregistreYesToujours faux : cet outil n’écrit jamais dans le dealflow.
quota_unitesNoUnités d’usage du jour : consommees_par_cet_appel…
avertissementNo
champs_absentsNoDonnées absentes du résultat partiel.
contradictionsYesContradictions CONFIRMÉES uniquement…
non_verifiableYesAffirmations que TOISE n’a pas pu confronter à une source…
limite_atteinteNoPrésent quand un quota, une limite d’offre ou une fonction…
paiement_requisNoPrésent quand le résultat complet est un achat à l’acte…
adresse_utiliseeNoAdresse effectivement vérifiée…
champs_financiersNoChamps prix/loyer/surface/rendement extraits…
ecarts_de_methodeYesÉcart hors fourchette TOISE, mais reposant sur une…
criblage_sanctionsNoCriblage des PERSONNES MORALES…
confiance_extractionNochamps_deduits, incoherences, non_retrouves : sortie brute…

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / criblage_sanctions
      Added value: +{
      +  "description": "Criblage des PERSONNES MORALES…",
      +  "type": "object"
      +}
  2. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond them: output is one verdict per claim, and 'une fourchette n'est jamais une erreur' pre-empts a likely false-positive interpretation of ranges. It says nothing about how unverifiable claims are reported or about non-real-estate input, which keeps it out of the top band.

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?

Two compact sentences, front-loaded with the verification action, then the false-positive caveat, then the sibling routing. Telegraphic phrasing ('Extraction seule des chiffres : toise_teaser') is efficient but slightly elliptic, and the parenthetical list duplicates the domain framing rather than adding new decision information.

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?

An output schema exists, so the verdict payload needn't be described, and annotations cover the read-only profile. However, for a tool that accepts an optional address the description never clarifies whether supplying 'adresse' changes the comparison basis, leaving a real gap relative to the tool's actual complexity.

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 only 50%: 'texte' carries a schema description and the tool description reinforces what such text contains, but the optional 'adresse' parameter is never mentioned or explained anywhere, and the 40-character minimum is not surfaced. At this coverage level the description should compensate for the undocumented parameter and does not.

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 specific verb plus resource ('Vérifier un teaser ou une dataroom') and enumerates exactly what gets checked (prix, propriétaire, permis, potentiel, risques) with the output unit stated ('un verdict par affirmation'). It also explicitly contrasts itself with the sibling toise_teaser, so an agent can distinguish the two without opening either 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 input situation (a pasted teaser or dataroom) and routes number-only extraction to toise_teaser. There is no explicit 'when not to use' (e.g. verified data already held internally), so it falls short of the fullest guidance, but the alternative is named with its selecting condition.

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