Skip to main content
Glama
Sign In

Marcel

by fr.marcel-retraite
OverviewDiscussionsAdmin

Comparer quatre rémunérations de dirigeant avec PER

simulate_remuneration_per
Read-onlyIdempotent

Compare quatre rémunérations d'un dirigeant de SASU : salaire seul, dividende seul, salaire et dividende, salaire, dividende et PER. Porte sur ces quatre stratégies ; pour comparer plusieurs niveaux de salaire, avec l'allocation chômage, voir compare_remuneration. Entrées : bénéfice, répartition, versement PER, tranche. Sortie : net immédiat, droits à retraite et capital retraite de chaque stratégie. 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": {
      "beneficeAvantIS": "<beneficeAvantIS>",
      "tmi": "<tmi>"
    },
    "name": "simulate_remuneration_per"
  }
}

Input Schema

NameRequiredDescriptionDefault
tmiYesTMI réel du dirigeant (ex: 0.41)
perVersementNoVersement PER annuel. Optionnel : le moteur applique son défaut.
rendementPERNoRendement annuel net du PER (défaut 0.04)
salaireChoisiNoSalaire brut choisi pour les stratégies C et D. Optionnel : le moteur applique son défaut.
beneficeAvantISYesBénéfice SASU avant IS
horizonRetraiteAnsNoHorizon retraite pour capitalisation PER (défaut 20 ans)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds value beyond that by disclosing the output contents (net immediately, pension rights, pension capital per strategy) and, importantly, that results are indicative and validated against 'cas de référence Marcel'. It stops short of stating default behaviour when optional inputs are omitted, which the schema covers instead.

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 four strategies are front-loaded in the first clause, followed by the routing note, then inputs and outputs. There is no filler, though the input/output enumeration is somewhat compressed and the field labels drift from the schema naming.

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 6-parameter simulation with no output schema, the description covers what is compared, what comes back, and the reliability caveat, which is what an agent needs. It omits that optional parameters fall back to engine defaults, but the schema states this for each optional field.

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 100%, so every parameter is already documented, and the baseline of 3 applies. The description's summary list ('bénéfice, répartition, versement PER, tranche') only loosely maps to the actual property names and introduces 'répartition' and 'tranche' wording that does not match the schema, adding little semantic value over structured data.

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 names a specific verb and scope: it compares exactly four remuneration strategies for a SASU director (salary alone, dividend alone, salary+dividend, salary+dividend+PER). It explicitly excludes the neighbouring case by pointing at compare_remuneration, so an agent can separate it from that sibling without inspecting schemas.

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?

Usage is stated positively (these four strategies) and negatively (for comparing several salary levels or unemployment allocation, use compare_remuneration). That is an explicit when/when-not pair with a named alternative, which is the top of the scale.

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

All Marcel toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources