Skip to main content
Glama

TOISE — intelligence foncière

Analyse par lot d’adresses ou de parcelles (20 au plus)

toise_lot
Read-only

Vérifier une liste de 1 à 20 adresses ou terrains d'un coup (sourcing en série) : un verdict par ligne. Offres payantes ; une étude décomptée par ligne traitée. Détail d'une ligne : toise_dossier_adresse.

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": {
      "lignes": "<lignes>"
    },
    "name": "toise_lot"
  }
}

Input Schema

NameRequiredDescriptionDefault
lignesYes1 à 20 lignes : chacune 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…
totalYesLignes à analyser dans cet appel…
echecsYes
curseurNo
partielNotrue : une source n’a pas répondu, des champs manquent…
sourcesYes
doublonsNo
has_moreYestrue si des lignes restent non traitées (quota ou délai).
reussiesYes
traiteesYes
warningsYes
resultatsYesUne entrée par ligne, dans l'ordre : statut ok | echec…
cout_quotaYes{ fonction, annonce (études au maximum pour cet appel)…
simulationYestrue : aucune analyse faite, aucun quota décompté.
lignes_luesYesLignes du tableau fourni.
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 toutes les lignes…
repartition_verdictsNoNombre de lignes par code de verdict…

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / lignes / description
      Previous value: -"1 à 20 lignes : chacune une adresse, ou un point…"New value: +"1 à 20 lignes : chacune une adresse, ou un…"
    • 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…"
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered; the description adds genuinely new behavior — that this is a paid offer and that one study/credit is deducted per processed line, which an agent must know before batching 20 rows. It does not explain the cursor's pagination behavior or whether partial results are returned on failure, which keeps it below a 5.

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?

Three compact sentences with the batch scope and row limit front-loaded, then cost, then the sibling pointer. No filler, though the dense colon-separated phrasing is slightly telegraphic and the cost/limit facts could be ordered more logically before the alternative-tool pointer.

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 values need no explanation, and the critical batch limit plus per-line billing are disclosed. The remaining gap is pagination: a 20-item cap with a "curseur" parameter strongly implies multi-page retrieval, and the description never says results can be continued or how many rows a page holds.

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 only reinforces the lignes bounds (1 to 20), which the schema already enforces via minItems/maxItems. The "curseur" parameter has no description anywhere and is never explained, and the per-line cost link to "simuler" is only implied; baseline 3 is appropriate since the schema does most of the work.

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 states a specific verb and resource — "Vérifier une liste de 1 à 20 adresses ou terrains d'un coup" — plus the output shape ("un verdict par ligne"). It also explicitly points to toise_dossier_adresse for single-line detail, so an agent can distinguish batch from single-address analysis 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?

The phrase "sourcing en série" frames the use case (bulk screening) and the closing sentence routes single-line inspection to toise_dossier_adresse, giving a clear alternative. It stops short of stating when NOT to batch (e.g. a one-off lookup, or a case where a cheaper single tool suffices), so it is strong but not fully explicit.

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