Academic Writer MCP

État des fournisseurs d'IA

get_ai_status

Read-onlyIdempotent

Check AI setup status to see local or connected mode, configured keys (not displayed), project consent, monthly token usage, and remaining steps to enable an AI provider.

Instructions

Mode local/connecté, clés configurées (jamais affichées), consentement du projet, tokens consommés ce mois, et étapes restantes pour activer un fournisseur d'IA.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_ai_status"
  }
}

Input Schema

Name	Required	Description	Default
`project_id`	No	Projet (pour voir son consentement).

Output Schema

Name	Required	Description	Default
`mode`	Yes
`connected`	Yes
`providers`	Yes
`auto_choice`	Yes
`data_notice`	No		En mode connecté, les extraits nécessaires à la tâche (dossier de section, texte à corriger ou à traduire) sont transmis au fournisseur choisi (Anthropic ou OpenAI) et traités sur ses serveurs, selon ses conditions. Les documents complets ne sont jamais envoyés. Le consentement est révocable.
`month_budget`	Yes
`how_to_enable`	Yes
`project_consent`	No
`default_provider`	Yes
`month_tokens_used`	Yes
`month_cost_estimate`	Yes	Uniquement si des tarifs ont été saisis.
`writing_engine_setting`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 9, 2026

TDQS

A3.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so safety is largely covered. The description still adds real behavioral context beyond them: keys are never displayed (a privacy guarantee) and the response reports consumption for the current month plus remaining activation steps, which tells the agent the data is diagnostic and non-mutating.

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?

One compact enumeration with the most decision-relevant fact (mode and key state) up front and no filler. It is a verbless fragment, which costs a little clarity but wastes no words.

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?

With an output schema present, the description needn't explain return shapes, and it correctly stays at the level of what facets are reported. Annotations and the single documented parameter cover the rest, so nothing essential for calling the tool correctly is missing.

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 100% and the single optional parameter is already documented as 'Projet (pour voir son consentement)'. The description echoes the consent linkage but adds no format, default, or scoping detail beyond the schema, so the baseline 3 applies.

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?

The description enumerates the exact status facets returned (local/connected mode, configured keys, project consent, monthly token usage, remaining activation steps), so the resource and scope are clear. It lacks an explicit verb phrase and never names a sibling to distinguish itself, but the enumerated content is specific enough to separate it from get_draft_status or detect_ai_indicators.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use sentence, no prerequisite, and no mention of alternatives such as test_ai_provider (to verify a key) or set_project_ai_consent (to change consent). The reader must infer from the field list that this is a diagnostic check, which is exactly the 'no guidance' case.

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

Deploy Server