Skip to main content
Glama

TOISE — intelligence foncière

Étude de marché d'un secteur

toise_etude_marche
Read-onlyIdempotent

Quel est le prix au m² d'un quartier : médiane, volumes de ventes par année, dispersion et tendance sur une ou plusieurs sections cadastrales. Entrée : code_insee + sections (6 au plus). Pas de médiane sous 5 ventes ; climat DRIAS. Ventes une à une : toise_dvf_historique.

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": {
      "code_insee": "<code_insee>",
      "sections": "<sections>"
    },
    "name": "toise_etude_marche"
  }
}

Input Schema

NameRequiredDescriptionDefault
sectionsYesSections cadastrales à agréger, six au plus…
code_inseeYes

Output Schema

NameRequiredDescriptionDefault
liensNoLiens vers la fiche TOISE et vers des services de…
quotaNoQuota du jour après cet appel : { fonction, limite…
lectureNo
partielNotrue : une source n’a pas répondu, des champs manquent…
periodeNo{ de, a } : années couvertes.
sourcesYes
has_moreNo
par_typeNotype, ventes, part_pct, prix_m2_median…
sectionsNo
tendanceNo{ de, a, prix_m2_avant, prix_m2_apres, evolution_pct…
warningsYes
par_anneeNo
proprieteNoStructure de propriété (personnes morales) de la commune…
code_inseeYes
base_medianeNoBase de la médiane publiée par cet outil : { outil…
quota_unitesNoUnités d’usage du jour : consommees_par_cet_appel…
surface_batiNo{ mediane_m2, min_m2, max_m2 } ; null avec…
avertissementNo
evolution_pctNoÉvolution du prix médian entre les deux dernières années…
motif_absenceNoRenseigné quand aucune mutation n’a été relevée.
champs_absentsNoDonnées absentes du résultat partiel.
climat_projeteNoDRIAS TRACC-2023 au centre de la commune : { disponible…
dispersion_pctNoÉcart interquartile, en % du premier quartile.
prix_m2_medianNo
limite_atteinteNoPrésent quand un quota, une limite d’offre ou une fonction…
paiement_requisNoPrésent quand le résultat complet est un achat à l’acte…
total_mutationsYesToutes les mutations relevées, dépendances comprises.
sections_muettesNoSections sans résultat : source sans réponse, ou section…
motif_absence_prixNoPourquoi prix_m2_median/dispersion_pct manquent, quand ils…
valeur_mediane_eurNo
premier_quartile_m2No
ventes_exploitablesYesVentes retenues pour le prix au m²…
troisieme_quartile_m2No
motif_absence_tendanceNoPourquoi la tendance manque, quand elle manque.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / climat_projete
      Added value: +{
      +  "description": "DRIAS TRACC-2023 au centre de la commune : { disponible…",
      +  "type": "object"
      +}
  2. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: no median is reported below 5 sales (a suppression rule the agent must anticipate) and a DRIAS climate layer is included. It remains silent on latency, coverage limits and what happens if a section has too few sales overall.

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?

Compact and front-loaded: the question and outputs come first, then inputs, then constraints, then the redirect to the sibling. The telegraphic fragments ('Pas de médiane sous 5 ventes ; climat DRIAS') are dense but each carries information, though 'climat DRIAS' is dropped without explanation of how it relates to the result.

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 not be spelled out, and the description still previews the key metrics. Combined with the required inputs, the section cap, the 5-sale threshold and the sibling redirect, this is sufficient for correct invocation; only the code_insee format and per-section failure behavior are left implicit.

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%: the sections array carries a description, but code_insee is an undocumented string. The description partially compensates by framing the input as code_insee + sections and restating the six-section cap, implying code_insee is a commune identifier, but it never specifies format or the INSEE-level granularity explicitly. Baseline 3 is appropriate.

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 the exact quantity computed (prix au m²) and enumerates the concrete outputs — médiane, volumes de ventes par année, dispersion, tendance — scoped to one or more cadastral sections. This is a specific verb+resource statement that an agent can distinguish from generic zone-comparison or transaction-listing siblings.

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 required input shape, caps the request at six sections, and explicitly redirects agents wanting sale-by-sale data to toise_dvf_historique. It stops short of naming when not to use it (e.g. commune-wide comparison vs. toise_comparer_zones), so context is clear but exclusions are partial.

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