Skip to main content
Glama

TOISE — intelligence foncière

Mission : trouver des actifs selon une stratégie d’investissement

toise_mission_opportunites
Read-only

Trouver des actifs qui correspondent à une stratégie d'investissement : criblage gratuit d'un département ou d'une commune, puis shortlist mesurée (30 candidats au plus). Pas un balayage exhaustif. Coût : une étude par candidat mesuré.

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_mission_opportunites"
  }
}

Input Schema

NameRequiredDescriptionDefault
code_inseeNo
departementNo
budget_mesureNoNombre de candidats mesurés (25 par défaut).
ticket_max_m2NoDoctrine (après mesure) : surface de…
ticket_min_m2NoDoctrine (après mesure) : surface de…
patrimoine_maxNoDoctrine (pré-filtre) : taille maximale…
patrimoine_minNoDoctrine (pré-filtre) : taille minimale du…
forme_juridiqueNoDoctrine (pré-filtre) : forme juridique…
densification_minNoDoctrine (après mesure) : écart minimal…
rendement_cible_pctNoDoctrine déclarative : rendement visé (%).
denomination_prefixeNo
personne_morale_priveeNoDoctrine (pré-filtre) : écarte les…
locaux_min_sur_parcelleNoDoctrine (pré-filtre) : nombre minimal de…

Output Schema

NameRequiredDescriptionDefault
coutYes{ fonction, candidats_mesures…
liensNoLiens vers la fiche TOISE et vers des services de…
quotaNoQuota du jour après cet appel : { fonction, limite…
curseurYes
lectureNo
partielNotrue : une source n’a pas répondu, des champs manquent…
sourcesYes
doctrineNoCritères de doctrine appliqués.
has_moreYes
warningsYes
millesimeNo
perimetreYes{ type: commune|departement, code }.
shortlistYesUn candidat mesuré par entrée : parcelle_id…
non_mesuresNoParmi les candidats retenus pour la mesure, ceux non…
quota_unitesNoUnités d’usage du jour : consommees_par_cet_appel…
budget_mesureYes
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…
avertissement_couvertureYesRappel explicite, toujours présent : shortlist parmi les…
candidats_bruts_prefiltreYesCandidats trouvés au pré-filtre déterministe (D1, gratuit)…
candidats_ecartes_au_prefiltreYescandidats_bruts_prefiltre moins les candidats effectivement…

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / densification_min / description
      Previous value: -"Doctrine (après mesure) : écart minimal entre…"New value: +"Doctrine (après mesure) : écart minimal…"
    • changedInput schema / properties / patrimoine_max / description
      Previous value: -"Doctrine (pré-filtre) : taille maximale, pour…"New value: +"Doctrine (pré-filtre) : taille maximale…"
    • changedInput schema / properties / personne_morale_privee / description
      Previous value: -"Doctrine (pré-filtre) : écarte les bailleurs…"New value: +"Doctrine (pré-filtre) : écarte les…"
    • changedInput schema / properties / ticket_max_m2 / description
      Previous value: -"Doctrine (après mesure) : surface de terrain…"New value: +"Doctrine (après mesure) : surface de…"
    • changedInput schema / properties / ticket_min_m2 / description
      Previous value: -"Doctrine (après mesure) : surface de terrain…"New value: +"Doctrine (après mesure) : surface de…"
  2. Changed1 schema field changed
    • changedInput schema / properties / locaux_min_sur_parcelle / description
      Previous value: -"Doctrine (pré-filtre) : nombre minimal de locaux…"New value: +"Doctrine (pré-filtre) : nombre minimal de…"
  3. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, destructiveHint=false and non-idempotency, so safety is covered; the description adds genuinely new behavior: free screening, a capped measured shortlist, and per-candidate metering. One tension: it says '30 candidats au plus' while the schema allows budget_mesure up to 1000, so the effective ceiling is ambiguous when both are read together.

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 short sentences, front-loaded with the purpose, then the mechanics, then the cost. Dense and nearly waste-free, though internal jargon ('criblage', 'shortlist mesurée', 'étude') is used without definition for a first-time agent.

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 13-parameter, zero-required mission tool with an output schema present, the description covers what the agent most needs: the two-stage flow, the non-exhaustive scope, and that each measured candidate costs an étude. It leaves the meaning of 'mesure' and the interplay between the stated 30-candidate cap and budget_mesure unstated, which is a moderate but not fatal gap.

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 77%, so the schema already documents most of the 13 parameters, including the doctrine filters and budget_mesure. The description adds only indirect meaning — 'un département ou d'une commune' hints at the departement/code_insee choice, and 'une étude par candidat mesuré' ties to budget_mesure — but never explains the pre-filter vs post-measure split that the schema labels in French shorthand.

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?

States a specific verb and resource ('Trouver des actifs qui correspondent à une stratégie d'investissement') plus the two-stage mechanics (free screening, then measured shortlist). It also scopes itself negatively ('Pas un balayage exhaustif'), which lets an agent separate it from an exhaustive census-style tool 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?

The description gives a clear usage context — a strategy-matching mission rather than a sweep — and states the cost model ('Coût : une étude par candidat mesuré'), which is a real decision input when choosing this tool. It stops short of naming an alternative sibling (e.g. toise_criblage) as the route for an exhaustive pass, so the exclusion is implied rather than routed.

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