Skip to main content
Glama

TOISE — intelligence foncière

Mes suivis, alertes et enregistrements

toise_suivis
Read-onlyIdempotent

Surveiller ou suivre des adresses : les adresses et zones DÉJÀ suivies sur le compte et leurs alertes (lecture seule ; créer une veille : toiseai.com/compte). Sections synthese, biens, equipe.

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_suivis"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoSection recherches : fiche d'une recherche.
typeNoSection recherches : carte ou portefeuille.
limiteNo
curseurNo
origineNoSection alertes : événements des veilles…veille
sectionNosynthese
id_apresNoSection comparaison : identifiant de la…
id_avantNoSection comparaison : identifiant de la…
non_luesNoSection notifications : seulement les non…
referenceNo

Output Schema

NameRequiredDescriptionDefault
liensNoLiens vers la fiche TOISE et vers des services de…
notesNo
quotaNoQuota du jour après cet appel : { fonction, limite…
totalYesNombre réel d'éléments de la section, avant pagination…
equipeNoSection equipe : role, nb_membres, delegations_donnees…
sourceYes
curseurYes
partielNotrue : une source n’a pas répondu, des champs manquent…
rapportNoSection rapport : du, au, total_terrains, par_statut…
sectionYes
sourcesYes
affichesYes
decalageNo
elementsNoÉléments de la section…
has_moreYes
non_luesNoSection notifications : nombre total de non lues.
syntheseNoSection synthese : compteurs { biens_suivis, zones_suivies…
warningsYes
millesimeNo{ valeur:null, motif } : données du compte, à jour au…
comparaisonNoSection comparaison : meme_hash, avant, apres…
quota_unitesNoUnités d’usage du jour : consommees_par_cet_appel…
lecture_seuleNoRappel : la création de suivis se fait sur…
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…
absence_de_resultatNoPrésent si la section est vide : cause et lecture…

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / id_apres / description
      Previous value: -"Section comparaison : identifiant de la version…"New value: +"Section comparaison : identifiant de la…"
    • changedInput schema / properties / id_avant / description
      Previous value: -"Section comparaison : identifiant de la version…"New value: +"Section comparaison : identifiant de la…"
    • changedInput schema / properties / non_lues / description
      Previous value: -"Section notifications : seulement les non lues."New value: +"Section notifications : seulement les non…"
  2. Changed1 schema field changed
    • changedInput schema / properties / origine / description
      Previous value: -"Section alertes : événements des veilles (biens)…"New value: +"Section alertes : événements des veilles…"
  3. First observed

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so 'lecture seule' is largely redundant. The description adds the useful constraint that only already-tracked items are returned and where creation happens, but says nothing about pagination behavior or result shape beyond what the output schema covers.

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 front-loaded sentence with the read-only constraint and the creation alternative placed early. The trailing section list is short but incomplete, which slightly undercuts its value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter, multi-section tool, the description omits how sections map to parameters and only partially lists them, so an agent cannot reliably choose a section from the description alone. The output schema and annotations cover safety and returns, but the section-selection gap is significant.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 10 parameters and only 60% schema coverage, the description should compensate, but it only names three sections (synthese, biens, equipe) while the schema enum lists eleven — an incomplete and potentially misleading enumeration. It adds no meaning for id, type, origine, curseur, limite, or the comparison/notification parameters.

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 resource (addresses/zones already tracked on the account and their alerts) and a clear read-only scope, and explicitly separates itself from creating a watch (pointing to toiseai.com/compte). The opening verb 'Surveiller ou suivre' is slightly ambiguous for a read-only tool, but 'DÉJÀ suivies' and 'lecture seule' resolve it.

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?

Gives one useful routing rule: to create a watch, go to the website rather than this tool. However, it offers no guidance on which of the 11 sections to request or when to prefer this over sibling tools, leaving section selection to inference.

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