Academic Writer MCP

Créer une sauvegarde

create_backup

Creates a local backup of your database, documents, drafts, exports, and configuration as a complete ZIP or database-only archive, excluding API keys; restore via CLI with Claude closed.

Instructions

Sauvegarde locale : complète (.zip : base + documents, rédactions, exports, configuration) ou base seule. Les clés API ne sont jamais incluses. La restauration se fait en ligne de commande (« uv run academic-writer restore <fichier.zip> --yes »), Claude fermé.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_backup"
  }
}

Input Schema

Name	Required	Description	Default
`complete`	No

Output Schema

Name	Required	Description	Default
`kind`	Yes
`path`	Yes
`size_mb`	Yes
`created_at`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 9, 2026

TDQS

A4.2/5.0

Behavior4/5

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

The annotations already declare write, non-destructive, non-idempotent, and closed-world behavior. The description adds useful context: API keys are never included, and restoration requires a separate CLI command with Claude closed. It does not cover destination path, overwrite behavior, or backup size, so it falls short of a 5.

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 three concise sentences, front-loaded with backup scope and followed by exclusions and restore instructions. The CLI example is useful and no wording is redundant.

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?

For a simple one-parameter mutation with an output schema, the description covers scope, exclusions, and the restore path. Minor operational details such as destination path and file naming are left to the output schema or omitted, but are not critical for correct invocation.

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

Parameters4/5

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

There is one boolean parameter with 0% schema description coverage, and the description compensates by defining the two modes: complete ZIP vs database only. This clearly maps to the complete parameter, though it could be more explicit about true/false and default behavior.

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 local backup and explicitly defines the two content modes: a complete ZIP with database, documents, drafts, exports, and configuration, or database only. This is specific enough to distinguish the tool from export/archive siblings and to understand what resource is created.

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?

It explains the complete vs base-only choice and notes that restoration is done manually via CLI with Claude closed. However, it does not explicitly say when to use this tool instead of archive_project or export_document, nor does it guide which backup mode to choose, so usage is implied rather than fully directed.

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

Deploy Server