Academic Writer MCP

Enregistrer un brouillon

save_section_draft

Saves section text as a proposed revision after automatic checks, preventing accidental overwrites so edits can be reviewed safely.

Instructions

Enregistre un texte rédigé par l'assistant (ou fourni par l'utilisateur) comme révision PROPOSÉE, après contrôles automatiques. Rien n'est écrasé.

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>",
      "text": "<text>"
    },
    "name": "save_section_draft"
  }
}

Input Schema

Name	Required	Description	Default
`kind`	No		draft
`note`	No
`text`	Yes	Texte de la section en Markdown (sans son titre).
`language`	No	Langue du texte (obligatoire pour une traduction) ; par défaut celle du projet.
`project_id`	Yes
`section_id`	Yes
`parent_revision_id`	No

Output Schema

Name	Required	Description	Default
`id`	Yes
`kind`	Yes
`note`	No
`text`	Yes
`model`	Yes
`checks`	Yes
`engine`	Yes
`status`	Yes
`version`	Yes
`language`	Yes
`created_at`	Yes
`decided_at`	No
`project_id`	Yes
`section_id`	Yes
`word_count`	Yes
`section_title`	Yes
`parent_revision_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 9, 2026

TDQS

B3.4/5.0

Behavior4/5

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

Annotations already say readOnly=false, destructiveHint=false, idempotentHint=false, so the description usefully adds that the result is only a PROPOSED revision, that automatic checks run first, and that nothing is overwritten. It omits what happens when the automatic checks fail and whether repeated calls create duplicate revisions, which matters given 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 action and closed with the most important guarantee ('Rien n'est écrasé'). No filler, though the parenthetical about authorship slightly interrupts the flow.

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 proposal/overwrite semantics are covered. But for a 7-parameter write tool with 29% schema coverage, the description leaves key parameters and validation-failure behavior undocumented.

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 29% across 7 parameters, yet the description explains none of them. The meanings of kind (draft/rewrite/translation/correction), note, and parent_revision_id are left entirely to bare schema titles.

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?

States a specific verb and outcome: saves an assistant- or user-authored text as a PROPOSED revision after automatic checks. That distinguishes it from sibling mutation tools like rewrite_academic_section or translate_academic_section, though no sibling is named explicitly.

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?

Implies usage (after text has been drafted, to persist it as a proposal rather than apply it) and notes the text may come from the assistant or the user. However, it gives no explicit when-not guidance or reference to the sibling tools that produce or apply revisions.

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

Deploy Server