Contribution exceptionnelle sur les hauts revenus (CEHR) — CEHR due sur le revenu fiscal de référence (art. 223 sexies CGI). Distincte de la CDHR. (sources: CGI art. 223 sexies ; BOFiP BOI-IR-CHR)
| Name | Required | Description | Default |
|---|---|---|---|
| situation | No | Situation familiale (seuils célibataire 250 k / couple 500 k). | Célibataire |
| revenu_fiscal_reference | Yes | Revenu fiscal de référence du foyer (€). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations present, the description alone must disclose behavior, but it only states the tax and its legal basis — nothing about what the tool returns, whether it is a read-only computation, or what side effects exist. It also does not explain how the contribution amount is derived (rates, brackets) beyond the schema's threshold hints. The agent is left to infer that this is a calculation tool.
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 compact two-sentence block with the key name, basis, and a disambiguation note front-loaded. The only flaw is a small redundancy ('Contribution exceptionnelle sur les hauts revenus (CEHR) — CEHR ...'), and the legal citations are arguably useful but not strictly necessary. Overall it is highly readable and wastes little space.
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 simple two-parameter tool, the schema plus description cover the inputs well, but the absence of an output schema puts the burden on the description to state what the tool returns (e.g., the computed CEHR amount). The description does not describe the output, rate application, or any failure cases. This leaves the definition minimally viable but not fully complete.
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%: both parameters have descriptions, including the 250k/500k threshold note for situation. The description adds little beyond this because it merely restates that CEHR is due on the revenu fiscal de référence, which the parameter already names. Baseline 3 applies since the schema already carries the parameter meaning.
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 the tool as concerned with the 'Contribution exceptionnelle sur les hauts revenus (CEHR)' due on 'revenu fiscal de référence', giving a clear resource and scope via the legal article. It explicitly distinguishes CEHR from CDHR, helping with disambiguation. The main weakness is the lack of an explicit verb such as 'calculate' or 'estimate' — the wording is more definitional than operational, though intent is clear.
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 description signals that this tool is for CEHR, not CDHR, which is a form of when-not guidance, and the legal references reinforce the domain. However, none of the sibling tools (e.g., fiscal_impot_revenu, fiscal_prelevements_sociaux, fiscal_tmi) are named or contrasted, so an agent gets no explicit routing guidance among the similar fiscal_* tools. Usage context is implied rather than spelled out.
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.