Academic Writer MCP

Indices de rédaction par IA

detect_ai_indicators

Read-onlyIdempotent

Analyze a document for AI-related indicators across style, metadata, provenance, and integrity, returning cautious evidence for human review rather than definitive proof.

Instructions

Analyse complète d'un document : style, métadonnées, historique, provenance, intégrité. Conclusion prudente : « indéterminée » par défaut ; une autre catégorie seulement si une déclaration technique explicite existe (C2PA, IPTC, outil nommé). Jamais de pourcentage. Indices pour un examen humain, jamais des preuves ; aucune décision ne doit reposer sur ce seul résultat.

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": {
      "document_id": "<document_id>"
    },
    "name": "detect_ai_indicators"
  }
}

Input Schema

Name	Required	Description	Default
`document_id`	Yes

Output Schema

Name	Required	Description	Default
`basis`	Yes	Ce sur quoi repose la conclusion.
`style`	Yes
`limits`	Yes
`audit_id`	Yes
`filename`	Yes
`metadata`	Yes
`integrity`	Yes
`conclusion`	Yes
`confidence`	No		non calibrée
`provenance`	Yes
`document_id`	Yes
`report_path`	No
`recommendations`	Yes
`report_markdown`	No
`conclusion_label`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 9, 2026

TDQS

A3.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so safety is covered. The description then adds real behavioral substance: it discloses the output policy (default conclusion 'indeterminate', another category only with an explicit technical declaration such as C2PA, IPTC or a named tool, never a percentage) and the evidentiary caveat that indicators are for human review. It does not describe latency, cost, or document-size limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening sentence is a well front-loaded list of analyzed dimensions, but the remainder is a dense, multi-clause disclaimer with nested parentheticals and typographic quotes that reads as policy text rather than instruction. It is not bloated, yet the output-policy rules are buried instead of being stated as discrete sentences.

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?

An output schema exists, so return-value explanation is not required, and annotations cover the read-only/idempotent profile. What the description supplies instead is the interpretive contract (default indeterminate, no percentages, human review only), which is the part an agent could otherwise get wrong; the only omission is any hint about what document_id refers to.

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?

Schema description coverage is 0% and there is one required parameter, document_id, which the description never explains in terms of format, source, or acceptable document types. Because only a single opaque identifier is involved and the description defines the analytical scope around the document, the gap is small; the description still fails to say where the document_id comes from.

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 names the object analyzed (a document) and enumerates the signal families examined: style, metadata, history, provenance, integrity. It does not name a specific distinguishing verb like 'detect' in isolation, and it never mentions the sibling differentiation (e.g. analyze_writing_patterns or analyze_document_metadata), but the scope is clear enough for an agent to know this is a multi-signal AI-authorship assessment.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no sibling is named as the alternative for narrower analyses even though analyze_writing_patterns and analyze_document_metadata clearly overlap. The only usage-direction content is the caution that results must not drive a decision alone, which constrains interpretation rather than selection.

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

Deploy Server