Skip to main content
Glama

Companero – Romanian Company Data

by ro.companero
OverviewDiscussionsAdmin

get_financial_health

Keywords: indicatori financiari, lichiditate, solvabilitate, profitabilitate, marjă, Altman Z, bonitate, analiză financiară, sănătate financiară, current ratio, quick ratio, cash ratio, debt to equity, leverage, working capital, net margin, operating margin, ROE, ROA, turnover growth, revenuePerEmployee, financial ratios, liquidity, solvency, financial health, company health, financial analysis, balance sheet ratios, indicatori bilanț, poziționare industrie, industry position, CAEN percentile, financial score, financial indicators.

Calculează și returnează indicatori financiari determiniști pentru o firmă românească după CUI, din bilanțurile ANAF (și surse publice agregate pentru ani mai vechi). Calcul pur, fără LLM — rezultate instant, cost marginal zero.

Grupe de indicatori: lichiditate (currentRatio, quickRatio, cashRatio) · solvabilitate / structură (debtToEquity, leverageRatio, workingCapital) · profitabilitate (netMargin, operatingMargin, roe, roa) · eficiență / dinamică (receivablesDays, turnoverGrowth, employeeGrowth, revenuePerEmployee) · Altman Z″-score (model academic: „zona sigură" Z″>2.6, „zona gri" 1.1–2.6, „zona de presiune financiară" <1.1; cu componente X1–X4) · poziționare în industrie față de percentilele P25/median/P75 din industry_pulse_agg (turnover, profit, angajați, segmentul CAEN × județ cu fallback național; disponibil doar pentru segmente ≥ 30 firme).

Două tier-uri (detail):

  • detail: "summary" (DEFAULT, FREE): netMargin + leverageRatio + turnoverGrowth pentru ultimul an cu bilanț + poziționare față de industrie. „Cum stă firma față de concurență?" (Lichiditatea și Altman Z″ apar doar în full, unde există date — bilanțul ANAF simplificat nu le conține pentru majoritatea firmelor.)

  • detail: "full" (GRATUIT, dar CERE CONT): toți indicatorii pe toți anii disponibili (serie multi-an) + Altman Z″ cu componente + poziționare vs. ambele segmente (CAEN × județ și național) + nota metodologică. Folosește pentru due diligence complet, analiză de credit, comparație competitivă.

IMPORTANT — interpretare:

  • null pe un indicator = necalculabil din lipsă de date (microentitățile nu raportează toate câmpurile bilanțului). null ≠ 0.

  • Altman Z″ este un model academic — nu un verdict sau rating Companero. Prezintă zonele cu denumirile academice.

  • Capitaluri proprii ≤ 0 → debtToEquity și roe emit flag negativeEquity.

Când îl folosești:

  • „Care e lichiditatea / solvabilitatea firmei X?"

  • „Cum se compară cifra de afaceri a firmei Z cu industria ei?"

  • „Ce indică Altman Z-score pentru firma W?"

  • „Evoluția marjei nete în ultimii 5 ani la firma V"

  • Due diligence financiar pre-colaborare (furnizor, client, partener)

  • Analiză de credit sau factoring · screening B2B

Cost: GRATUIT pe ambele tieruri. detail: "full" cere însă un cont: la un apel anonim pornește fluxul de autorizare, iar summary rămâne disponibil fără cont.

Confirmarea costului: un apel care ar consuma credite are nevoie de confirm: true. Fără el primești DEVIZUL (cost în credite și RON, soldul contului, alternativa gratuită dacă există) și nu se consumă nimic — reia apoi EXACT același apel cu confirm: true, după ce omul a acceptat costul.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taxIdYesRomanian CUI (Cod Unic de Înregistrare).
detailNo"summary" (free, anonymous) or "full" (free as well, but requires an account).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / detail / description
      Previous value: -"\"summary\" (free, default) or \"full\" (paid, see ActionCostCatalog)."New value: +"\"summary\" (free, anonymous) or \"full\" (free as well, but requires an account)."
  2. Changed1 schema field changed
    • removedInput schema / properties / confirm
      Removed value: -{
-  "description": "Acordul utilizatorului de a consuma credite pentru acest apel. Fără el, apelul întoarce DEVIZUL (cost, sold, alternativa gratuită) și nu consumă nimic. Nu îl trimite din proprie inițiativă: întreabă întâi omul.",
-  "type": "boolean"
-}
  3. First observed

TDQS

A4.3/5.0
Behavior5/5

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

With no annotations, the description carries the full behavioral burden and does so: it discloses the pure-computation/no-LLM nature, the free cost on both tiers, that `detail: "full"` triggers an authorization flow for anonymous callers while `summary` stays anonymous, the `confirm: true` deviz-then-rerun mechanism, and that the confirm/cost paragraph is generic boilerplate. It also documents edge semantics beyond structured data: `null` means uncalculable (≠ 0), negative equity emits a `negativeEquity` flag, and industry positioning requires segments of ≥30 firms with the 1.1/2.6 Z″ zone boundaries.

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?

The body is well structured with bolded group headers and bullets, but the opening is a large SEO-style keyword dump in two languages that adds search-surface noise rather than selection value. The trailing cost/confirm paragraph is generic boilerplate that states the tool is free on both tiers, making its 'credits would be consumed' scenario largely non-applicable here.

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?

No output schema exists, so the description must explain returns — and it does, listing every indicator group, the tier-dependent payload, the Altman Z″ component breakdown, industry percentile basis, and the `null`/`negativeEquity` conventions. Slightly reduced because the priority-order and default behavior of `detail` are stated but the actual response shape per tier is described narratively rather than precisely.

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 coverage is 100%, so the baseline is 3, but the description substantially enriches the `detail` parameter beyond the schema's one-line gloss: `summary` is DEFAULT and FREE, returns netMargin + leverageRatio + turnoverGrowth for the latest year plus industry position, while `full` is multi-year and adds Altman Z″ components and duel-segment positioning. taxId is only glossed as 'Romanian CUI', but that identifier is well understood.

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+resource: 'Calculează și returnează indicatori financiari determiniști pentru o firmă românească după CUI, din bilanțurile ANAF', and enumerates the exact indicator groups produced. The purpose is unambiguous, but it never explicitly contrasts itself with the sibling get_balance_sheets (raw statements) versus this computed-ratio tool, so the differentiation is implicit rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Includes a dedicated 'Când îl folosești' section with concrete trigger phrasings ('Care e lichiditatea / solvabilitatea firmei X?', Altman Z questions, margin evolution) plus named scenarios (due diligence pre-collaborare, credit/factoring analysis, B2B screening). It also gives the selection rule between the tool's own tiers: use `summary` for the competitive-position question, `full` for complete due diligence / credit analysis.

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

All Companero – Romanian Company Data toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources