Academic Writer MCP

Insérer une citation

insert_citation

Adds a citation marker after a passage and creates a proposed revision without overwriting text; rejects suspect, missing, or divergent sources unless explicitly forced.

Instructions

Ajoute un appel [@clé] après un passage : crée une révision PROPOSÉE (rien n'est écrasé). Refuse une source suspecte, introuvable ou divergente, sauf décision explicite de l'utilisateur.

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>",
      "source_key": "<source_key>",
      "anchor_text": "<anchor_text>"
    },
    "name": "insert_citation"
  }
}

Input Schema

Name	Required	Description
`claim`	No	Affirmation étayée par la source (traçabilité).
`force`	No	Citer une source douteuse sur décision explicite de l'utilisateur.
`locator`	No	Localisation : « с. 15 », « p. 15 », « chap. 2 ».
`project_id`	Yes
`section_id`	Yes
`source_key`	Yes
`anchor_text`	Yes	Passage exact et unique de la section après lequel citer.

Output Schema

Name	Required	Description
`marker`	Yes	Marqueur inséré dans le texte (stable, indépendant du style).
`source`	Yes
`message`	Yes
`revision_id`	No	Nouvelle révision proposée contenant le marqueur.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 9, 2026

TDQS

A3.8/5.0

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 that the write lands in a PROPOSED revision and that nothing is overwritten, plus the refusal conditions for untrusted or conflicting sources. That is real behavioral context an agent cannot get from the annotation block alone.

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?

Two sentences, no filler, and the most consequential fact (nothing is overwritten) is capitalized and placed early. Every clause carries information.

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 non-idempotent mutation tool with an output schema, the description covers the safety profile, the revision semantics, and the refusal/force policy. It stops short of explaining what happens when `anchor_text` is not unique or does not match, which the schema hints at but does not resolve.

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

Parameters3/5

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

The description implicitly covers three of the seven parameters: `anchor_text` ('après un passage'), `source_key` ('[@clé]'), and `force` ('sauf décision explicite de l'utilisateur'). It adds nothing about `claim`, `locator`, `project_id`, or `section_id`, leaving the 57% schema coverage gap partly unfilled.

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 effect: it adds a Pandoc-style citation call `[@clé]` after a passage. That is concrete enough for an agent to identify the operation without reading the schema, though it does not differentiate itself from any sibling by name.

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?

Usage is implied rather than spelled out: the tool is used when a passage needs a citation attached. It does give one useful decision rule (refusal on suspicious/missing/divergent sources unless the user explicitly decides otherwise), but no alternatives or prerequisites are named.

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

Deploy Server