Academic Writer MCP

Vérifier les calculs

validate_calculations

Read-onlyIdempotent

Recalculate arithmetic, rounding, and units in a document or project draft to catch inconsistent or redefined symbols without judging formulas or source data.

Instructions

Recalcule les calculs écrits (« v = ω·r = 10·0,05 = 0,5 м/с ») d'un document importé (document_id) ou de la rédaction d'un projet (project_id) : arithmétique, arrondis, unités (SI, notations fr/ru/en), symboles définis puis réutilisés, symboles redéfinis avec une autre valeur. Ne juge ni les formules ni les données.

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": "validate_calculations"
  }
}

Input Schema

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

Output Schema

Name	Required	Description	Default
`ok`	Yes
`label`	Yes
`checks`	Yes	Écarts d'abord ; les calculs justes sont résumés au-delà de 40.
`notice`	No		Contrôle de l'arithmétique et des unités écrites. Ne valide ni le choix des formules, ni les données d'entrée, ni l'interprétation : relecture humaine indispensable.
`rounding`	Yes
`conflicts`	Yes
`mismatches`	Yes
`definitions`	Yes
`unit_mismatches`	Yes
`decimal_separators`	No
`calculations_checked`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 9, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so safety is covered; the description adds genuine value by enumerating the checks performed (arithmetic, rounding, SI and fr/ru/en unit notations, symbol definition/reuse/redefinition) and by delimiting what the tool will not assess. It does not discuss cost, limits, or how findings are reported, but the presence of an output schema lowers the need.

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?

Two sentences, the first front-loading the action with an inline example and the scope list, the second stating the limitation. Dense but every clause carries information; only the parenthetical example costs slight length that a shorter illustration would have avoided.

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 two-parameter read-only validation tool with an output schema and rich annotations, the description covers purpose, scope and the meaning of both inputs. The single remaining shortfall is the unresolved document_id vs. project_id combination rule, which is the same gap flagged under parameter semantics.

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?

Schema description coverage is 0%, so the description must carry parameter meaning: it does so by tying document_id to an imported document and project_id to a project's draft. The critical gap is that both parameters are optional with null defaults, and the description never states whether exactly one is required, which wins if both are supplied, or what happens if neither is given.

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 gives a precise verb and resource ('Recalcule les calculs écrits ... d'un document importé ou de la rédaction d'un projet') and backs it with a concrete example ('v = ω·r = 10·0,05 = 0,5 м/с'). The scope list (arithmetic, rounding, units, defined/reused/redefined symbols) plus the exclusion 'Ne juge ni les formules ni les données' separates it from a formula-evaluation sibling.

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 through the two source paths the parameters name (imported document vs. project draft) and through the negative scope clause about not judging formulas or data. However, no alternative tool is named and no explicit when-to-use/when-not rule is stated, so the agent must infer routing from sibling names.

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

Deploy Server