Skip to main content
Glama

tax-retirement

by io.github.herve-coulon

retraite_progressive

Retraite progressive (fraction de pension + temps partiel) — Fraction de pension perçue en travaillant à temps partiel en fin de carrière (art. L161-22-1-5). Depuis le 01/09/2025, accessible dès 60 ans (décret 2025-681) avec 150 trimestres. Fraction = 100 % − quotité travaillée (salarié 40-80 %, fonction publique 50-90 %, TNS : baisse de revenus 20-60 %). Continue d'acquérir des droits. (sources: CSS art. L161-22-1-5, D161-2-24 (décret 2025-681), R351-39, R351-41 ; Service-Public F12842)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ageYesÂge actuel (≥ 60 depuis le 01/09/2025).
rfrNo
partsNo
statutNoStatut (insensible à la casse/accents). Reconnus : "salarié" (défaut), "fonctionnaire", "profession libérale" / "TNS" / "indépendant". Détermine la plage de quotité.
date_effetNoDate d'effet de la retraite progressive (YYYY-MM-DD).
trimestresYesTrimestres acquis (≥ 150 requis).
date_naissanceNoYYYY-MM-DD — recale l'âge min pour une date d'effet < 01/09/2025.
quotite_travailYesQuotité de temps partiel (0-1). Salarié 0,40-0,80 ; FP 0,50-0,90.
diminution_revenusNoTNS uniquement : baisse de revenus (0,20-0,60) — alternative à quotite_travail.
pension_brute_annuelleNoPension totale brute annuelle (base + comp.) — chiffre la fraction en €.

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden, and it exposes core behavior: the fraction formula, status-specific ranges, eligibility conditions, and continued rights accrual. It does not disclose edge-case behavior or output/error handling, but for a calculation tool the underlying logic is unusually well specified.

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 description is dense but mostly earns its length: definition, formula, legal context, eligibility, status variations, and rights acquisition are all relevant. The source citations at the end add some clutter, but the core definition and formula are front-loaded.

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?

For a complex 10-parameter tool with no annotations and no output schema, the description covers legal and calculation rules well, but leaves operational gaps. It never states what the tool returns, how invalid or ineligible inputs are handled, or how to resolve the schema tension where quotite_travail is required even though diminution_revenus is described as an alternative for TNS.

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 description coverage is 80%, so the input schema already documents most parameters and the baseline is 3. The description adds useful domain meaning around status-specific quotity ranges and the TNS income-reduction alternative, but it does not systematically map its prose to parameters like date_effet, date_naissance, rfr, or pension_brute_annuelle.

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?

The description gives the tool a precise subject: 'Retraite progressive (fraction de pension + temps partiel)' and defines it as the pension fraction received while working part-time at the end of a career, with legal basis and calculation formula. It does not explicitly state an action like 'calcule' or 'estime', nor does it contrast with sibling tools, so it is clear but not maximally differentiated.

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?

The description provides strong contextual signals: since 01/09/2025, eligibility at age 60 with 150 quarters, and status-specific quotity ranges. However, it never says when to prefer this tool over siblings such as retraite_estimation, retraite_optimisation, or retraite_pension_regime, nor does it give explicit when-not-to-use guidance.

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

All tax-retirement toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation4/5

The tool families are clearly separated by domain prefixes (fiscal, retraite, referentiel), and the descriptions proactively distinguish near-neighbors such as fiscal_tmi vs fiscal_prelevements_sociaux and retraite_estimation vs retraite_pension_totale. Some initial confusion is possible between retraite_pension_regime and retraite_regimes, but the descriptions are detailed enough to resolve it.

Naming Consistency4/5

Most tools follow a predictable snake_case domain_object pattern: fiscal_*, retraite_*, referentiel_*. The clear outlier is qotien_capacites, which uses a misspelled, non-domain prefix and breaks the otherwise consistent naming scheme.

Tool Count3/5

With 18 tools, the server is heavier than the typical 3-15 sweet spot, though it is organized into recognizable fiscal, retirement, and referential clusters. The count is defensible for a two-domain server, but it begins to feel like a large MCP surface that agents must navigate carefully.

Completeness4/5

The server covers the main French income-tax and retirement calculation needs: income tax, marginal rate, social levies, CEHR, property capital-gains surtax, pension estimation, multi-regime totals, net pension, buybacks, progressive retirement, and parental surcharge. Minor gaps exist—such as no explicit long-career early-retirement tool and pensions_fournies being referenced rather than exposed as a first-class tool—but agents can work around them.

Resources