Skip to main content
Glama

Mesurer l'écart avec un revenu cible à la retraite

marcel_find_gap
Read-onlyIdempotent

Calcule l'écart entre le revenu projeté à la retraite et un objectif, et l'effort d'épargne mensuel en PER et en assurance-vie qui le comble. Porte sur l'écart et l'effort ; pour la pension elle-même, voir marcel_estimate_pension ; pour la projection patrimoniale complète, marcel_financial_twin. Entrées : année de naissance, revenu mensuel, revenu imposable annuel, pension brute ou net fourni avec sa provenance, objectif. Sortie : écart, effort mensuel par enveloppe. Sans net chiffrable, la pension nette est null. Calcul couvert par des cas de référence Marcel : résultat indicatif.

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": {
      "birthYear": "<birthYear>",
      "monthlyIncome": "<monthlyIncome>"
    },
    "name": "marcel_find_gap"
  }
}

Input Schema

NameRequiredDescriptionDefault
rfrNoRFR d'avis d'impôt. Requis avec brut + parts pour un net foyer.
rfrYearNoAnnée de l'avis d'imposition, pas celle des revenus. Pour une pension versée en 2026, elle vaut 2025.
rfrValueNo
birthYearYesAnnée de naissance
pensionNetNoNet fourni avec provenance. Alternative : RFR d'avis + brut → fiscaliserFoyer.
nombrePartsNoParts fiscales. Distinct du nombre de pensionnés.
tauxCsgSaisiNo
monthlyIncomeYesRevenu mensuel net en euros
retirementAgeNoÂge cible de retraite
existingAssetsNoActifs existants et leur revenu mensuel estimé
estimatedPensionNoNet de pension pris en compte seulement avec pensionNetSource=caller_provided.
pensionNetSourceNoMarque estimatedPension comme flux fourni.
pensionBrutMonthlyNoPension brute de liquidation.
annualTaxableIncomeNoRevenu net imposable annuel
nombrePensionnesFoyerNoPensionnés du foyer. Distinct du nombre de parts.
targetRetirementIncomeNoObjectif de revenu mensuel à la retraite

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: the output shape ('écart, effort mensuel par enveloppe'), a documented edge case ('Sans net chiffrable, la pension nette est null'), and a caveat that results are indicative and covered by Marcel reference cases. It does not state assumptions behind the effort calculation (horizon, returns), which keeps it from a 5.

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?

The sentence order is well front-loaded: purpose first, then scope and alternatives, then inputs, then output and caveats. The input enumeration partially duplicates the schema, which is the only wasted material; otherwise the text earns its place.

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?

For a 16-parameter tool with nested objects and no output schema, the description covers purpose, sibling routing, output shape, the null-pension edge case, and a result disclaimer. Remaining gaps are defaults and assumptions (retirementAge default, how existingAssets feed the calculation), but no critical calling information is missing.

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 88%, so the schema already documents nearly every parameter, including the provenance/status consts and the parts-vs-pensionnés distinctions. The description enumerates the main inputs and flags the 'pension brute ou net fourni avec sa provenance' alternative path, which adds mild value, but it is largely a restatement of what the schema provides; baseline 3 applies.

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 opens with a specific verb and resource: it computes the gap between projected retirement income and a target, plus the monthly savings effort in PER and assurance-vie needed to close it. It explicitly scopes itself as 'porte sur l'écart et l'effort' and names two sibling tools it is not, so an agent can distinguish it without opening the schema.

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 routes the agent away explicitly: 'pour la pension elle-même, voir marcel_estimate_pension ; pour la projection patrimoniale complète, marcel_financial_twin'. That is clear context plus alternatives. However, the closest sibling, marcel_revenue_at_retirement, is never mentioned, leaving the main ambiguity unresolved.

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.