Liste des régimes de retraite calculables par points — Découverte : renvoie les régimes en points calculables via retraite_pension_regime (code, libellé, machine, étage, valeur de service 2026, taux de réversion). Filtrable par famille. (sources: retraite_registre.js (source unique des 47 régimes) ; references_officielles.json v0.8.6)
| Name | Required | Description | Default |
|---|---|---|---|
| famille | No | Filtrer par famille (facultatif). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It discloses the return content ('code, libellé, machine, étage, valeur de service 2026, taux de réversion'), the fixed scope ('source unique des 47 régimes'), and the data sources. This gives an agent a clear picture of a read-only discovery lookup, though it does not discuss pagination or auth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single well-structured sentence: purpose, output fields, filter option, and sources all appear without filler. The front-loaded 'Découverte' immediately signals intent, and every clause earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a low-complexity tool with one optional parameter and no output schema, this description is sufficient. It names the exact fields returned, states the universe of data (47 régimes), explains the filter, and points to the downstream tool for calculation. 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.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%: the only parameter, 'famille', is fully documented with an enum and 'Filtrer par famille (facultatif).' The description merely restates 'Filtrable par famille', adding no new semantic value. Baseline 3 is therefore appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description identifies a specific action ('Liste', 'renvoie') on a specific resource ('régimes de retraite calculables par points') and clarifies that this is a discovery tool, not a computation tool. It also references retraite_pension_regime, making its role relative to the calculation tool explicit. This clearly separates it from siblings like retraite_estimation or retraite_optimisation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The 'Découverte' label gives a clear context: this is for discovering point-based régimes before using retraite_pension_regime. It does not explicitly list when not to use it or name sibling alternatives, so it falls just short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
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.
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.
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.
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.