Skip to main content
Glama

Outil.io

Record accounting expense

record_accounting_expense

Comptabiliser une dépense : montants HT et TVA déductible en CENTIMES EUR, fournisseur, référence, date, compte de charge et lien HTTPS du justificatif. Aucune écriture bancaire avant règlement.

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": {
      "requestId": "<requestId>",
      "data": "<data>"
    },
    "name": "record_accounting_expense"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataYes
requestIdYesUUID stable pour les reprises de la même opération ; nouvel UUID si les données changent

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so safety is covered. The description adds genuinely non-obvious behavior: amounts must be expressed in EURO CENTS, VAT must be deductible, and no bank entry is generated until payment is settled. It does not mention duplicate handling or what happens on retry, though the schema's requestId description partly covers that.

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 dense sentences, no filler. The unit convention (CENTIMES) is capitalized and front-loaded, and the settlement caveat is placed last as a scoping note, which is the right order for an agent scanning the definition.

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 write tool with a nested payload, no output schema and only partial schema descriptions, the description covers units, required business fields, and the side-effect boundary. Missing pieces are the meaning of `name`/`account` codes and any indication of what is returned (e.g. a document identifier) for follow-up calls.

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 50% (only requestId is documented), so the description must carry weight, and it does: it establishes that net and vat are in CENTS and in EUR, that vat is the deductible portion, and that receiptUrl is an HTTPS link to the supporting document. The `name` field and the meaning of the account codes (601, 606, ...) are left to the agent's accounting knowledge, which is a real gap.

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 opening clause 'Comptabiliser une dépense' states a specific verb and resource, and the enumeration of what the record contains (HT/VAT amounts, supplier, reference, date, expense account, receipt link) pins down scope precisely. It stops short of naming a sibling, but the closing note 'Aucune écriture bancaire avant règlement' implicitly separates it from record_accounting_payment without naming it.

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?

'Aucune écriture bancaire avant règlement' tells the agent this tool books the expense only and that settlement is a separate step, which is useful implied routing. However, it never explicitly says when to use this versus reverse_accounting_expense or record_accounting_payment, leaving the agent to infer the alternatives.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.