Academic Writer MCP

Corriger une section

correct_academic_section

Proposes a corrected academic section using safe LanguageTool fixes and optional AI review, explaining each change and rejecting edits that alter numbers or add proper nouns.

Instructions

Propose une version corrigée : corrections LanguageTool sûres (termes du projet et formules protégés), puis IA. Une correction IA qui modifie un chiffre ou ajoute un nom propre est écartée. Chaque correction est expliquée. Le résultat est une révision PROPOSÉE.

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>",
      "section_id": "<section_id>"
    },
    "name": "correct_academic_section"
  }
}

Input Schema

Name	Required	Description
`engine`	No
`use_ai`	No	Compléter par l'IA (accords, cas subtils) si un moteur est disponible.
`project_id`	Yes
`section_id`	Yes
`revision_id`	No	Version à corriger ; par défaut l'acceptée ou la dernière.

Output Schema

Name	Required	Description
`brief`	No
`engine`	Yes	languagetool, languagetool+<moteur IA> ou assistant
`ai_used`	Yes
`applied`	Yes	Corrections appliquées dans la révision proposée, avec explication.
`message`	Yes
`revision`	Yes
`ai_discarded`	Yes	Correction IA écartée car elle modifiait le sens (chiffres, noms).
`remaining_suggestions`	Yes	Signalements non appliqués automatiquement.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 9, 2026

TDQS

B3.2/5.0

Behavior4/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses meaningful behavior: protected project terms and formulas are preserved by the safe LanguageTool pass, AI corrections that alter a number or introduce a proper noun are discarded, and every correction is explained. The statement that the result is a proposed revision clarifies that nothing is silently applied. What is missing is whether a revision is persisted, what happens when no engine is available, and any cost or rate considerations for the AI pass.

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?

Three short sentences, front-loaded with the core action and the correction order, with no filler. The all-caps PROPOSÉE earns its emphasis by carrying the key non-destructive guarantee. Slightly terse for the amount of behavior it is compressing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value explanation is fairly excused, and the safety model is well covered. For a five-parameter tool with 40% schema coverage and several plausible sibling alternatives, however, the description leaves engine selection and tool-choice reasoning entirely to inference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 40% across five parameters, so the description is expected to compensate and does not. It never explains the engine options (auto, assistant, ollama, anthropic, openai), the use_ai toggle, or how revision_id interacts with the default of accepted-or-latest. The one hint, 'puis IA', vaguely gestures at use_ai but adds no operational meaning.

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 states a specific action on a specific resource: it proposes a corrected version of a section, first with safe LanguageTool fixes then with AI. That is far more than a restatement of the name. It does not, however, contrast itself with nearby siblings such as rewrite_academic_section, improve_academic_style or check_language, so an agent must infer which one applies.

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 explicit statement of when to choose this tool over rewrite_academic_section, improve_academic_style or check_language, nor any when-not guidance. The only implied context is that the output is a PROPOSED revision rather than an applied one, which hints at a review-then-accept workflow but is never spelled out.

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

Deploy Server