Academic Writer MCP

Audit qualité final

final_quality_audit

Run a final pre-submission audit of calculations, claims, consistency, structure, assignment requirements, references, and unvalidated sections, then get a blocking/fix/ready-for-human-review verdict and Markdown report.

Instructions

Audit complet avant remise : calculs, affirmations, cohérence, structure, exigences confirmées des consignes, et pour un projet : sections non validées et audit des références. Verdict : bloquant / à corriger / prêt pour la relecture humaine (jamais « validé »). Rapport Markdown dans le dossier exports.

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": "final_quality_audit"
  }
}

Input Schema

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

Output Schema

Name	Required	Description
`label`	Yes
`counts`	Yes
`issues`	Yes	Constats triés par gravité (au plus 150).
`limits`	No
`verdict`	Yes
`audit_id`	Yes
`summaries`	Yes	Résumé par contrôle.
`by_category`	Yes
`report_path`	No
`requirements`	No
`verdict_label`	Yes
`report_markdown`	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 declare readOnlyHint=false and destructiveHint=false, so the write nature is already known; the description usefully specifies what the write is (a Markdown report saved in the exports folder) and defines the verdict taxonomy while explicitly stating it never returns 'validated'. It does not cover non-idempotency (repeated runs presumably create new reports) or runtime cost, which keeps it below 5.

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?

Dense but front-loaded: scope first, then verdict categories, then output location. The enumerated checklist lists are terse and each element earns its place, though the verdict sentence and report sentence could be merged slightly.

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-value detail is not required, and the verdict semantics are well covered. The gap is inputs: with zero schema coverage and two optional identifiers, the agent cannot tell mode selection or the effect of save_report=false, which matters for an audit that writes a file.

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% for all three parameters, so the description must compensate — and it largely does not. The mention 'et pour un projet' hints that project_id activates the extra project-mode checks, but document_id and save_report (and whether the two ids are mutually exclusive) are never explained.

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 a specific verb ('Audit complet') and enumerates the audited dimensions: calculs, affirmations, cohérence, structure, exigences confirmées, plus project-only sections non validées and reference audit. It is clearly the aggregate check rather than a single-dimension sibling like check_consistency or audit_references, but it never names those siblings, so differentiation is implicit.

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?

The phrase 'avant remise' establishes the usage moment (pre-submission), which is genuine context. However, there is no statement about when to prefer the narrower sibling audits, no prerequisites, and no exclusion conditions, so the agent must infer the choice.

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

Deploy Server