Skip to main content
Glama

retraite_estimation

Read-onlyIdempotent

Estimation de pension (données partielles) — Pension approchée à partir du statut, du revenu, de l'âge et de l'âge de départ : carrière reconstituée, SAM plafonné au PASS, décote. Rend un point central, une fourchette et un niveau de confiance. Ce N'est PAS un calcul certain — il remplace un relevé de carrière (RIS) manquant, pas l'inverse. Si le relevé de carrière ou de caisse est connu, préférer le calcul exact : régime en points → retraite_pension_regime ; fonction publique, régimes spéciaux, IEG → retraite_pension_annuites ; plusieurs régimes → retraite_pension_totale. (sources: CNAV — taux plein 50 %, SAM 25 meilleures années plafonné au PASS ; Agirc-Arrco — barème de points 2026 ; PASS 2026 = 48 060 € ; Fonction publique — 75 % du traitement indiciaire)

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": {
      "statut": "<statut>",
      "revenu_net_imposable": "<revenu_net_imposable>",
      "age": "<age>"
    },
    "name": "retraite_estimation"
  }
}

Input Schema

NameRequiredDescriptionDefault
ageYesÂge actuel (ans).
statutYesStatut (insensible à la casse et aux accents). Valeurs reconnues : "salarié cadre", "salarié non-cadre" (ou "salarié" seul = non-cadre), "fonctionnaire", "profession libérale" / "TNS" / "indépendant" (= libéral).
teaserNoAperçu gratuit, sans paiement : true renvoie le chiffre de tête avec sa confiance et ses sources (free preview, no payment).
age_departNoÂge de départ souhaité (défaut 64).
trimestres_acquisNoTrimestres déjà acquis (RIS) — resserre la fourchette si fourni.
annee_debut_carriereNoAnnée de début de carrière — resserre la fourchette si fournie.
revenu_net_imposableYesRevenu net imposable annuel actuel (€).
traitement_indiciaireNoFonctionnaire uniquement : dernier traitement indiciaire brut annuel, hors primes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / teaser
      Added value: +{
      +  "default": false,
      +  "description": "Aperçu gratuit, sans paiement : true renvoie le chiffre de tête avec sa confiance et ses sources (free preview, no payment).",
      +  "type": "boolean"
      +}
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, closed-world), so the description is free to add the things annotations cannot: the return shape (point central, fourchette, niveau de confiance), the confidence caveat, and the computational assumptions (SAM capped at PASS, 25 meilleures années, taux plein 50%, décote). The 'replaces a missing RIS, not the reverse' framing is exactly the kind of epistemic disclosure an agent needs to avoid over-trusting the output.

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?

Front-loaded with the purpose, then the caveat, then the alternative-routing rule — a sensible order with no filler sentences. The trailing parenthetical source list (PASS 2026, barème Agirc-Arrco 2026) is dense and earns its place as credibility/versioning context, though it slightly lengthens an otherwise tight description.

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

Completeness5/5

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

There is no output schema, so the description must explain returns — and it does (central value, range, confidence level). For a read-only estimator with 8 fully documented parameters, the caveats, the methodology and the sibling routing together leave nothing an agent needs in order to call it correctly or interpret the answer.

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 100% and each parameter already carries its own description, so the schema does the heavy lifting. The prose nonetheless adds meaning beyond it by naming the four drivers (statut, revenu, âge, âge de départ) and by implying via the RIS framing that trimestres_acquis and annee_debut_carriere are the optional precision knobs — a small but real addition over the schema text.

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?

States a specific verb and resource ('Estimation de pension') and immediately bounds the scope: approximation from statut, revenu, âge and âge de départ, with a named methodology (carrière reconstituée, SAM plafonné au PASS, décote). It also declares what it is not ('Ce N'est PAS un calcul certain'), which lets an agent separate it from the exact-calculation siblings 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?

Gives an explicit when-to-use condition (missing RIS / relevé de carrière) and a when-not with three named alternatives routed by regime type: points → retraite_pension_regime, fonction publique/spéciaux/IEG → retraite_pension_annuites, multi-régimes → retraite_pension_totale. The selection rule is fully specified rather than inferred.

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.