Academic Writer MCP

Consentement au traitement externe

set_project_ai_consent

Idempotent

Grant or revoke permission to send project excerpts to external AI providers, with scope and explicit user confirmation, so academic writing assistance respects consent.

Instructions

Accorde ou révoque l'autorisation d'envoyer des extraits de ce projet à un fournisseur d'IA externe.

N'appeler pour accorder QUE si l'utilisateur l'a demandé explicitement et a tapé lui-même la phrase de confirmation, après lui avoir expliqué quelles données partent et vers qui.

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": {
      "project_id": "<project_id>",
      "granted": "<granted>"
    },
    "name": "set_project_ai_consent"
  }
}

Input Schema

Name	Required	Description	Default
`scope`	No		all
`granted`	Yes	true pour accorder, false pour révoquer.
`project_id`	Yes
`user_confirmation`	No	Pour accorder : phrase tapée PAR L'UTILISATEUR, exactement « J'autorise l'envoi externe ». Ne jamais la remplir à sa place.

Output Schema

Name	Required	Default
`consent`	Yes
`message`	Yes
`project_id`	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.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 9, 2026

TDQS

A4.4/5.0

Behavior4/5

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

The annotations already declare a non-read-only, idempotent, non-destructive mutation. The description adds valuable behavior beyond that: external data transfer of project excerpts, recipient disclosure, and a mandatory user-typed confirmation phrase. It does not specify post-revocation effects or data-retention behavior, so it stops short of full transparency.

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?

The description is front-loaded with the tool's purpose, followed by a compact mandatory usage condition. Every sentence contributes to either purpose or safe invocation, with no redundant wording.

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?

Given the output schema exists and annotations cover mutation/idempotency traits, the description supplies the key consent safeguards an agent needs before calling. The main gap is that scope selection and revocation effects are not described, which is noticeable for a consent tool with multiple provider options.

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?

With only 50% schema description coverage, the description partially compensates by explaining that project excerpts go to an external AI provider and that the confirmation phrase must be typed by the user. However, it does not explain the scope enum values ('all', 'anthropic', 'openai') or clarify the project_id parameter, leaving meaningful parameter ambiguity.

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 states a specific verb pair, 'accorde ou révoque', and a precise resource, 'l'autorisation d'envoyer des extraits de ce projet à un fournisseur d'IA externe'. This clearly distinguishes it from sibling tools like get_ai_status or test_ai_provider.

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?

It gives an explicit when-to-use condition for granting: only if the user has explicitly asked and typed the confirmation phrase themselves, after being told what data leaves and to whom. This is a strong safety-oriented usage rule with a clear exclusion, though revocation guidance is only implicit.

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

Deploy Server