Skip to main content
Glama
Sign In
francestudent-mcp

francestudent-mcp

by Yormede
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Générer une image (France Student)

fs_generate_image

Generates one or more PNG images from a text prompt through a France Student IA account, saves them to disk, and returns the image files or paths.

Instructions

Génère une ou plusieurs images avec le modèle gpt-image-2-codex via ton compte France Student IA (discussion incognito avec un agent OpenAI). Les PNG sont enregistrés sur le disque et renvoyés. Chaque image prend ~20-30 s et consomme du budget de chat France Student.

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": {
      "prompt": "<prompt>"
    },
    "name": "fs_generate_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
agentNoAgent OpenAI qui pilote l'outil d'image.gpt-6-sol
countNoNombre d'images (générées l'une après l'autre).
aspectNoFormat souhaité (indicatif : le modèle choisit la taille finale).auto
promptYesDescription de l'image (français ou anglais).
qualityNo'high' demande un rendu plus détaillé (indicatif).auto
keep_chatNoGarder la discussion France Student créée (par défaut elle est supprimée après téléchargement).
output_dirNoDossier de sortie (défaut : francestudent-mcp/output).
raw_promptNoEnvoyer le prompt tel quel, sans la consigne 'utilise ton outil d'image'.
return_imageNoRenvoyer l'image elle-même dans la réponse (sinon seulement le chemin).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4/5.0
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 does a fair job: it discloses that images take ~20-30 s each, that calls consume France Student chat budget, that an incognito discussion with an OpenAI agent is created on the user's account, and that PNGs are written to disk and returned. It stops short of describing failure behavior or whether existing files in the output directory are overwritten.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the action and model, then output, then cost/latency. Nothing is wasted and the most decision-relevant constraints come last but remain brief.

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 nine-parameter, no-annotation, no-output-schema tool, the description covers action, artifact, latency and cost, which is most of what an agent needs before calling. It does not mention the default chat-session deletion side effect exposed by keep_chat, which is the one meaningful behavioral gap for a tool that touches an external account.

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 all nine parameters (agent, count, aspect, quality, prompt, keep_chat, output_dir, raw_prompt, return_image) are already documented in the schema. The description only loosely echoes that multiple images can be produced, adding no meaning beyond what the schema states.

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 resource ("Génère une ou plusieurs images"), pins the model (gpt-image-2-codex) and the provider account, and states the output artifact (PNG files saved to disk and returned). An agent can tell immediately what this does and that it is unrelated to fs_list_agents and fs_usage.

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 context is only implied: the latency and budget warning ("~20-30 s et consomme du budget") signals this is a costly call to use sparingly, but there is no explicit when-to-use or when-not-to-use guidance, and no mention of alternatives or prerequisites.

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

Deploy Server

Other Tools