Skip to main content
Glama

Rapport complet

get_full_report
Read-onlyIdempotent

Rapport métier complet sur une période : CA (caisse + factures définitives, détail inclus), top produits, top clients, créances. Combine plusieurs analyses. La paie et le personnel sont exclus de ce serveur par conception, et aucun réglage ni aucun droit ne les ouvre : aucun outil ne donne accès aux salaires, aux bulletins de paie ni aux salariés, et aucun ne peut en établir ; ils se consultent seulement dans SAMA Entreprise. (Lecture seule.)

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": "get_full_report"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoPériode d'analyse en jours

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already carry readOnlyHint, idempotentHint and non-destructive, so the '(Lecture seule.)' tagline earns nothing. What the description does add beyond structured data is a hard scope boundary: payroll, payslips and employees are unreachable from this server by design and viewable only in SAMA Entreprise, which usefully stops an agent from hunting for a non-existent salary tool. It does not describe report shape, aggregation currency, or latency, so it stops short of 5.

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?

Well front-loaded — the report contents come first, in one dense sentence. But the payroll exclusion is restated three times in successive clauses ('exclus par conception… aucun réglage ni aucun droit… aucun outil… aucun ne peut en établir'), and '(Lecture seule.)' duplicates the annotation. Roughly half the text is one point said repeatedly, which costs it a point despite the good opening.

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 one-optional-param, read-only, non-destructive aggregate with no output schema, the description does the right job: it tells the agent what sections the report returns (revenue with detail, top products, top customers, receivables). Gaps are minor — period-window limits and whether amounts are multi-currency are unstated — but nothing needed to invoke it correctly is missing.

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?

There is a single optional parameter, days, and the schema already documents it at 100% coverage ('Période d'analyse en jours'). The phrase 'sur une période' merely echoes that field without adding format, bounds, or default behaviour. Baseline 3 applies since the schema does all the semantic work.

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?

Opens with a specific deliverable — a complete business report over a period — and enumerates its contents: revenue (cash register + final invoices with detail), top products, top customers, receivables. 'Combine plusieurs analyses' signals it is a composite, which separates it from the granular single-metric siblings. It never names a specific alternative report tool, so differentiation is inferential rather than explicit.

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 only implied: 'Combine plusieurs analyses' suggests this is a one-call rollup instead of chaining get_sales_report + get_top_products + get_top_customers, but that routing is never stated. The long payroll passage is a domain exclusion, not guidance about when to pick this tool over get_sales_full_analytics or get_dashboard_stats. No prerequisites, no when-not-to-use for the report itself.

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.

Resources