Academic Writer MCP

Réécrire une section

rewrite_academic_section

Rewrite an existing academic section from revision instructions and run a fidelity check that flags changed, removed, or added numbers, technical terms, and proper nouns.

Instructions

Propose une nouvelle version d'une section existante. Un contrôle de fidélité signale tout chiffre, terme technique ou nom propre modifié, supprimé ou ajouté.

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>",
      "instructions": "<instructions>"
    },
    "name": "rewrite_academic_section"
  }
}

Input Schema

Name	Required	Description
`engine`	No
`project_id`	Yes
`section_id`	Yes
`revision_id`	No	Version de départ ; par défaut la version acceptée ou la dernière proposée.
`instructions`	Yes	Ce qu'il faut changer (ton, concision, clarté, structure...).

Output Schema

Name	Required	Description
`brief`	No	Dossier à rédiger (moteur assistant).
`engine`	Yes
`revision`	No	Révision proposée (moteur serveur).
`next_step`	Yes
`engine_reason`	Yes

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?

Annotations only declare readOnlyHint=false, idempotentHint=false, destructiveHint=false and openWorldHint=true; the description adds meaningful behavior beyond that by disclosing a fidelity check that flags modified, removed or added figures, technical terms and proper nouns. It still does not say whether the result is persisted or only proposed, nor what happens to the prior revision, which matters given readOnlyHint=false and idempotentHint=false.

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?

Two short sentences, front-loaded with the core action and followed by the one genuinely surprising behavior. No filler, though the extreme brevity leaves the second sentence carrying behavior that arguably belongs in a fuller usage paragraph.

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 not be explained, and the fidelity-check sentence usefully previews part of the result. However, for a five-parameter generation tool with an engine selector and revision targeting, the description omits which revision is consumed, whether the proposal is saved, and how the engine choice affects output.

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%: revision_id and instructions carry descriptions in the schema, while engine, project_id and section_id are bare. The description mentions none of the five parameters, including the required 'instructions' and the engine choice ('auto','assistant','ollama',...), so it does not compensate for the coverage gap.

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 gives a specific verb and resource: 'Propose une nouvelle version d'une section existante', and adds the distinctive fidelity-check behavior. It does not distinguish this tool from close siblings such as correct_academic_section, improve_academic_style or write_academic_section, so the agent must infer the boundary from the name alone.

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?

Nothing states when to use this instead of correcting, translating, improving style, or writing a section from scratch. The only cue is the phrase 'section existante', which implicitly requires an existing section, but there is no guidance on prerequisites (e.g. an accepted revision) or exclusions.

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

Deploy Server