Skip to main content
Glama
Sign In

Marcel

by fr.marcel-retraite
OverviewDiscussionsAdmin

Comparer un même actif dans plusieurs enveloppes

compare_allocation
Read-onlyIdempotent

Compare le capital net après fiscalité d'un même actif détenu en PEA, assurance-vie, compte-titres personnel, compte-titres de société ou holding, à rendement identique. Entrées : montant, rendement, horizon, enveloppes candidates. Sortie : capital net par enveloppe et règles appliquées. 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": {
      "asset": "<asset>",
      "candidates": "<candidates>",
      "objective": "<objective>"
    },
    "name": "compare_allocation"
  }
}

Input Schema

NameRequiredDescriptionDefault
assetYes
objectiveYesObjectif patrimonial
candidatesYesVéhicules à comparer — minimum 2
situationFamilialeNoAbattement assurance-vie après 8 ans. seul : 4 600 euros, couple : 9 200 euros. Sans ce champ, l'abattement n'est pas appliqué.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuine context beyond them: the return payload includes the applied tax rules, and results are explicitly flagged as indicative ('résultat indicatif', covered by Marcel reference cases). It does not disclose validation failures (e.g. 400 on missing TMI) or pagination-style behavior, which is acceptable for a calculator.

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?

Front-loaded with the comparison itself, then a short input recap, output shape and a caveat — four sentences with little waste. The input list slightly duplicates the schema, keeping it from a 5.

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 read-only nested-object tool with no output schema, it does state what comes back (net capital per envelope plus applied rules) and warns the result is indicative. The gaps are the unmentioned objective/family-situation effects and the TMI prerequisites for certain account types, which live only in the schema.

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 75%, so the baseline is 3. The recap ('montant, rendement, horizon, enveloppes candidates') merely restates the obvious asset and candidates fields and omits both 'objective' and 'situationFamiliale' — the latter materially changes results (no allowance applied when absent) and deserves a mention in the description.

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?

States a precise verb and resource: comparing net-after-tax capital for the same asset held across PEA, AV, CTO, corporate CTO or holding, at identical return. The enumeration of envelope types implicitly sets it apart from the single-envelope simulators (simulate_pea, simulate_av), though no sibling is named outright.

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?

Usage is only implied by the scenario ('same asset, several envelopes, identical return'), with no explicit when-to-use/when-not or routing to alternatives such as simulate_pea/simulate_av for a single wrapper or compare_results for cross-scenario results. The minimum of 2 candidates is stated only in the schema, not the description.

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