Skip to main content
Glama

TOISE — intelligence foncière

Doctrines et mémoire du dealflow du compte

toise_dealflow
Read-onlyIdempotent

Suivi de dossier et dealflow : où en sont mes dossiers d'investissement (teasers, annonces, bilans, audits) et mes doctrines. Doctrines et dossiers de teasers du compte connecté, par décision. Lecture seule.

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_dealflow"
  }
}

Input Schema

NameRequiredDescriptionDefault
limiteNo
curseurNo
sectionNo
decisionNoNe lister que les dossiers de cette…

Output Schema

NameRequiredDescriptionDefault
liensNoLiens vers la fiche TOISE et vers des services de…
quotaNoQuota du jour après cet appel : { fonction, limite…
profilNoMoyennes mesurées sur les 200 dossiers les plus récents…
curseurNo
partielNotrue : une source n’a pas répondu, des champs manquent…
sectionYes
sourcesYes
dossiersYesDossiers de la page : { id, reference, score, decision…
has_moreYes
warningsYes
doctrinesYesDoctrines du compte : { id, intitule, criteres, cree_at }…
repartitionYesNombre réel de dossiers par décision, sur tout le dealflow…
quota_unitesNoUnités d’usage du jour : consommees_par_cet_appel…
champs_absentsNoDonnées absentes du résultat partiel.
motifs_absenceNoPour chaque section vide ou non demandée, le motif.
total_dossiersYesNombre réel de dossiers du compte…
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_doctrinesYes
doctrine_exempleNoCritères d’une doctrine d’exemple (modèle de saisie).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / decision / description
      Previous value: -"Ne lister que les dossiers de cette décision."New value: +"Ne lister que les dossiers de cette…"
  2. First observed

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint and openWorldHint, so 'Lecture seule' merely repeats structured data. What the description usefully adds is scope ('du compte connecté') and the content taxonomy (teasers, annonces, bilans, audits), but it says nothing about pagination behavior or result volume despite a curseur parameter.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the core purpose, but the second sentence largely restates the first ('Doctrines et dossiers de teasers du compte connecté' vs 'mes dossiers ... et mes doctrines') and 'Lecture seule' duplicates the annotation. Efficient in length, somewhat redundant in content.

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

Completeness3/5

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 annotations carry the safety profile. Still, with 4 optional parameters at 25% schema coverage and no mention of pagination (curseur) or result limits (limite), and no differentiation from the closely named sibling, an agent lacks enough to call it with full confidence.

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

Parameters4/5

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

Schema coverage is only 25%, so the description must compensate: it explains the 'decision' filter ('par décision') and its section enum values map onto the described content domains (doctrines, dossiers). It does not clarify 'limite' (1-50) or 'curseur' pagination semantics, leaving a residual gap, but the highest-value filters are covered.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource domains (investment dossiers with teasers, annonces, bilans, audits, plus doctrines) but uses a noun phrase ('Suivi de dossier et dealflow') rather than a specific verb, so the agent must infer this is a listing/reading tool. It also fails to distinguish itself from the near-identically named sibling toise_memoire_dealflow, which appears to cover the same memory-of-dealflow territory.

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?

'où en sont mes dossiers d'investissement ... et mes doctrines, par décision' implies the use case (checking portfolio/investment pipeline status filtered by decision) and 'du compte connecté' scopes it to the connected account. However, there is no explicit when-to-use versus alternatives, and no hint about how this differs from toise_memoire_dealflow.

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