Academic Writer MCP

Améliorer le style

improve_academic_style

Analyzes academic text for long sentences, repetition, vague wording, first-person usage, and style-rule issues, then optionally proposes a fidelity-checked rewrite.

Instructions

Analyse le style académique (phrases trop longues, répétitions, formulations vagues, première personne, règles de style LanguageTool) et, sur demande, propose une réécriture contrôlée (fidélité vérifiée).

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": "improve_academic_style"
  }
}

Input Schema

Name	Required	Description
`engine`	No
`rewrite`	No	Proposer aussi une réécriture corrigeant les problèmes relevés.
`project_id`	Yes
`section_id`	Yes
`revision_id`	No

Output Schema

Name	Required	Description	Default
`checks`	Yes
`message`	Yes
`rewrite`	No
`revision_id`	Yes
`languagetool_style`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 9, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true and destructiveHint=false, so the agent knows this may write and may call external services. The description adds meaningful behavior beyond that: rewriting is only proposed on request and output fidelity is verified, which reassures about safety of the rewrite. It does not disclose that an external LLM engine may be invoked, nor any model/cost implications of the engine choice.

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?

A single sentence, front-loaded with the analysis purpose and followed by the optional rewrite capability. There is no filler, though the parenthetical lists make it slightly dense.

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 values need no explanation, and the description adequately frames the analysis-versus-rewrite modes. However, for a 5-parameter tool with 20% schema coverage and an unexplained multi-provider engine parameter, key information an agent needs to call it correctly is missing.

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 coverage is only 20%; the schema documents only 'rewrite'. The description implicitly covers rewrite ('sur demande') but says nothing about 'engine', which accepts auto/assistant/ollama/anthropic/openai and is the most consequential parameter, nor about revision_id or how project_id/section_id scope the analysis. With low coverage the description should compensate and does not.

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 verb and resource ('Analyse le style académique') and enumerates the concrete checks performed (long sentences, repetitions, vague phrasing, first person, LanguageTool rules), plus an optional rewrite mode. It does not name or contrast itself with likely siblings such as check_language, correct_academic_section, or rewrite_academic_section, so differentiation is left to inference.

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?

'sur demande' signals that rewriting is opt-in via the rewrite flag, which implies a two-mode usage pattern. Beyond that there is no guidance on when to choose this tool over the sibling rewrite/correct/check tools, nor prerequisites such as needing an existing section or revision.

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

Deploy Server