Academic Writer MCP

Vérifier les affirmations

verify_factual_claims

Read-onlyIdempotent

Detects factual claims such as figures, dates, attributions and cited standards, then checks their traceability to verified citations, project documents and standard editions without judging truth.

Instructions

Repère les affirmations factuelles (chiffres, dates, « selon X », formulations absolues, normes citées) et contrôle leur TRAÇABILITÉ : citation [@clé] vers une source vérifiée, chiffres retrouvés dans les documents du projet, édition des normes. Ne déclare jamais une affirmation vraie ou fausse.

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": "verify_factual_claims"
  }
}

Input Schema

Name	Required	Description	Default
`project_id`	No
`document_id`	No

Output Schema

Name	Required	Description	Default
`label`	Yes
`claims`	Yes	Non étayées d'abord (au plus 120).
`notice`	No		Repérage de la traçabilité : aucune affirmation n'est déclarée vraie ou fausse. Chaque affirmation non étayée doit être vérifiée par une personne dans une source fiable, puis citée.
`by_support`	Yes
`claims_found`	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 readOnly, idempotent and closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavioral content: it defines what counts as evidence of traceability (a [@clé] citation to a verified source, figures located in project documents, standard editions) and imposes a hard constraint — 'Ne déclare jamais une affirmation vraie ou fausse' — which prevents the agent from expecting a verdict.

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, both load-bearing: the first front-loads what is detected and against which evidence; the second states the non-verdict constraint. No filler, no restatement of the title.

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 needn't be explained, and the read-only profile is covered by annotations. What is missing is the scope of operation, which is left ambiguous precisely because the two scoping parameters are undocumented in both the schema and the description.

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 0% and the description never mentions project_id or document_id at all. The agent must guess whether the tool scans one document, a whole project, or everything by default, and what the nullable defaults mean — a clear miss when the schema carries no semantics.

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 pair ('Repère ... et contrôle leur TRAÇABILITÉ') and enumerates the exact artifacts it targets (chiffres, dates, « selon X », formulations absolues, normes citées), which distinguishes it in substance from siblings like verify_source_metadata or audit_references. It never names a sibling, so routing relies on the agent recognizing the scope overlap itself.

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 by the scope statement — run it on a text to check whether factual claims are traceable to verified sources. There is no explicit when-to-use trigger, no when-not condition, and no pointer to the neighboring tools (verify_content_credentials, confirm_source_verification) that an agent would need to sequence this correctly.

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

Deploy Server