Skip to main content
Glama

TOISE — intelligence foncière

Score et rang d’un portefeuille d’actifs (50 au plus)

toise_portefeuille_lot
Read-only

Vérifier jusqu'à 50 adresses ou terrains d'un coup (sourcing en lot) : un score et un rang par actif. Offres payantes ; une étude par actif traité ; simuler: true annonce le coût.

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": {
      "actifs": "<actifs>"
    },
    "name": "toise_portefeuille_lot"
  }
}

Input Schema

NameRequiredDescriptionDefault
actifsYes1 à 50 actifs : chacun une adresse, ou un…
curseurNo
simulerNotrue : annonce le coût et le quota restant…

Output Schema

NameRequiredDescriptionDefault
liensNoLiens vers la fiche TOISE et vers des services de…
quotaNo{ limite, utilise, restant } après l'appel…
totalYesActifs à analyser dans cet appel…
echecsYes
curseurNo
lectureNoExplication du score : ordonne une pile de dossiers, ne…
partielNotrue : une source n’a pas répondu, des champs manquent…
sourcesYes
doublonsNo
has_moreYestrue si des actifs restent non traités (quota ou délai).
reussiesYes
traiteesYes
warningsYes
resultatsYesUne entrée par actif, dans l'ordre : statut ok | echec…
actifs_lusYesActifs du tableau fourni.
cout_quotaYes{ fonction, annonce (études au maximum pour cet appel)…
simulationYestrue : aucune analyse faite, aucun quota décompté.
non_traiteesYes
quota_unitesNoUnités d’usage du jour : consommees_par_cet_appel…
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…
quota_suffisantNoSimulation : le quota restant couvre-t-il tous les actifs à…
repartition_rangsNoNombre d’actifs par rang (potentiel, investiguer, neant).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / actifs / description
      Previous value: -"1 à 50 actifs : chacun une adresse, ou un point…"New value: +"1 à 50 actifs : chacun une adresse, ou un…"
  2. Changed1 schema field changed
    • changedInput schema / properties / simuler / description
      Previous value: -"true : annonce le coût et le quota restant, sans…"New value: +"true : annonce le coût et le quota restant…"
  3. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the description only needs to add cost/metering context — which it does: paid offering, one study charged per processed asset, and simuler:true to preview cost. What it omits is that the operation is non-idempotent (per annotations), i.e. re-running incurs another charge per asset, which would be the one piece of behavior an agent most needs before retrying.

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?

A single dense sentence front-loads the capability and the 50 cap, then appends cost terms separated by semicolons. Nothing is wasted, though "une étude par actif traité" is terse enough to be ambiguous about the exact billing unit.

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?

An output schema exists, so return shape needn't be described; the description covers the batch limit, the paid/metered model and the simulation flag. The remaining gaps — interplay with toise_portefeuille/toise_lot and how curseur continues a large portfolio — are modest for a 3-parameter tool.

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 67% and the description reinforces the two documented parameters: the 50-asset ceiling (already in maxItems) and simuler's cost-announcement role (already in the schema description). The third parameter, curseur, is undocumented in both schema and description, so pagination/resumption semantics remain unexplained.

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?

"Vérifier jusqu'à 50 adresses ou terrains d'un coup (sourcing en lot) : un score et un rang par actif" gives a specific verb (vérifier/scorer), a bounded resource (1-50 actifs) and the per-asset return (score + rang). It does not differentiate from the closely named sibling toise_portefeuille or from toise_lot, so an agent must still infer which batch entry point to choose.

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?

The phrase "sourcing en lot" implies the batch use case, and the billing note ("une étude par actif traité") hints at when this is costly, but there is no explicit when-to-use guidance and no named alternative for scoring a single asset or a non-batch portfolio.

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