TOISE — intelligence foncière

Lecture d’un teaser et adéquation à une doctrine

toise_teaser

Read-onlyIdempotent

Analyser un teaser ou un mémorandum d'investissement collé en texte : prix, loyer, rendement, durée ferme, chaque valeur avec son extrait. Confronte à la doctrine du compte (prioritaire, à examiner, hors cible). Lecture seule. Vérifier ses affirmations : toise_deal_verify ; enchaîner adresse et bilan : toise_acquisition.

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": {
      "texte": "<texte>"
    },
    "name": "toise_teaser"
  }
}

Input Schema

Name	Required	Description
`texte`	Yes	Texte du teaser collé (40 à 60 000 caractères).
`doctrine`	No	Critères de la doctrine, tous facultatifs…
`doctrine_id`	No

Output Schema

Name	Required	Description
`liens`	No	Liens vers la fiche TOISE et vers des services de…
`quota`	No	Quota du jour après cet appel : { fonction, limite…
`suite`	No
`champs`	Yes	Valeurs extraites : prix, loyer, surface, rendement, walb…
`curseur`	No
`partiel`	No	true : une source n’a pas répondu, des champs manquent…
`preuves`	Yes	Pour chaque champ, l’extrait du texte dont il provient…
`sources`	Yes
`doctrine`	Yes	Doctrine appliquée et son origine : { origine…
`has_more`	Yes
`warnings`	Yes
`manquants`	Yes	Parmi prix, loyer, surface, typologie : ce que le texte ne…
`adequation`	Yes	score (0-100 ou null), couverture_pct, decision…
`enregistre`	Yes	Toujours faux : cet outil n’écrit jamais dans le dealflow.
`quota_unites`	No	Unités d’usage du jour : consommees_par_cet_appel…
`avertissement`	No
`champs_absents`	No	Données absentes du résultat partiel.
`motifs_absence`	No	Pour chaque champ null, le motif.
`limite_atteinte`	No	Présent quand un quota, une limite d’offre ou une fonction…
`paiement_requis`	No	Présent quand le résultat complet est un achat à l’acte…
`alerte_rendement`	No	Écart entre rendement annoncé et recalculé ; null avec…
`rendement_recalcule_pct`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so 'Lecture seule' is largely redundant. What does add value is the disclosure that every extracted value comes 'avec son extrait' (source provenance) and that the doctrine comparison yields one of three verdicts (prioritaire, à examiner, hors cible) — behavioral traits not encoded in the annotations.

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 front-loaded sentences with no filler: extraction scope, doctrine verdicts, then read-only plus routing. The compressed '(prioritaire, à examiner, hors cible)' and the telegraphic 'Vérifier… ; enchaîner…' pattern are efficient but slightly clipped for an unfamiliar 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?

With an output schema present and full annotations, the description needn't explain return values, and it covers extraction scope, doctrine comparison and tool chaining. The remaining gap is the doctrine/doctrine_id interaction, which neither schema nor description resolves.

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 schema itself describes the nested doctrine criteria and the text length bounds. The description only hints at doctrine handling via 'la doctrine du compte', leaving the precedence between the inline `doctrine` object and `doctrine_id` — the main ambiguity an agent faces — unexplained. Baseline 3 is appropriate given 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 gives a precise verb ('Analyser') and resource ('un teaser ou un mémorandum d'investissement collé en texte'), then enumerates the extracted fields (prix, loyer, rendement, durée ferme) and the three-way doctrine verdict. An agent can distinguish it from toise_deal_verify or toise_acquisition without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the input precondition (text pasted in), and explicitly routes follow-ups: 'Vérifier ses affirmations : toise_deal_verify ; enchaîner adresse et bilan : toise_acquisition'. The verification and pipeline alternatives are named with the condition that selects them.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All TOISE — intelligence foncière tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?