Skip to main content
Glama

Companero – Romanian Company Data

by ro.companero
OverviewDiscussionsAdmin

get_market_stats

Keywords: statistici industrie/sector, medie cifra de afaceri pe sector, cifra de afaceri mediană, mediana profitului, câte firme active/noi/radiate, percentile P25/median/P75, benchmark de piață, mărimea pieței, market sizing, cod CAEN, industrie, județ, market statistics, industry/sector stats, median turnover, average revenue by sector, company counts by industry/county Romania, new vs dissolved companies, market benchmark, percentiles.

Statistici AGREGATE pentru un segment de piață din România (o industrie SAU un cod CAEN de clasă, opțional restrâns la un județ). Returnează: număr de firme active, firme noi și radiate în anul curent, și percentilele P25 / mediană / P75 pentru cifra de afaceri, profit și număr de angajați — plus un trend multi-anual. Datele vin din bilanțurile ANAF + registrul ONRC, precalculate; percentilele există doar pe segmente cu ≥30 de firme cu bilanț (altfel fallback pe percentilele naționale, marcat prin usedNationalFallback; segmentul local prea mic e semnalat în smallSegment).

Segmentul se dă prin EXACT UNUL dintre:

  • caenCode: cod CAEN de clasă, 4 cifre (ex. "6201" software la comandă, "0111" cultura cerealelor). Codurile de 2–3 cifre NU sunt suportate (percentilele nu se pot agrega din percentile) — folosește un cod de 4 cifre sau industry.

  • industry: nume, slug sau id al uneia dintre cele 34 de industrii Companero (ex. "IT și software", "Imobiliare"). Dacă nu știi valoarea, apelează list_industries. Opțional county (nume sau id, ex. "Cluj") pentru statistici județene și year pentru count-urile unui an anume (percentilele rămân pe anul de referință).

Când îl folosești:

  • „Care e cifra de afaceri mediană a firmelor de software din Cluj?"

  • „Câte firme s-au înființat / radiat în construcții anul acesta?"

  • „Câte firme active sunt în industria imobiliară?"

  • „Cât câștigă în medie o firmă de contabilitate?" (mediană + P25/P75)

  • „Cât de mare e piața pentru CAEN 6201?" / „market sizing pe un sector"

  • Context de piață înainte de a evalua o firmă individuală.

Disambiguare (NU confunda cu):

  • search_companies GĂSEȘTE FIRME individuale — folosește-l pentru „top N firme după cifra de afaceri" sau liste/export. get_market_stats dă STATISTICI de segment, nu firme.

  • list_industries = taxonomia (id/nume/slug ale industriilor).

  • get_cpv_market = piața ACHIZIȚIILOR PUBLICE (SEAP), nu piața comercială.

  • get_financial_health = poziționarea UNEI firme față de industria ei.

Gratuit.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
yearNoAn opțional pentru count-uri (default: anul de referință). Percentilele rămân pe anul de referință.
countyNoJudeț opțional (nume sau id, ex. "Cluj"). Omite pentru statistici naționale.
caenCodeNoCod CAEN de clasă (4 cifre, ex. "6201"). Exclusiv cu `industry`.
industryNoIndustrie Companero — nume, slug sau id (ex. "IT și software"). Exclusiv cu `caenCode`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • removedInput schema / required
      Removed value: -[]
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses data provenance (ANAF balance sheets + ONRC registry, precomputed), the ≥30-firms threshold for percentiles, the national-fallback behavior flagged via usedNationalFallback, the smallSegment signal, and that the tool is free.

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 organized into purpose, selection rules and disambiguation, but it opens with a large bilingual keyword dump that is largely SEO noise for an agent and inflates the size. The substantive content earns its place; the keyword block does not.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a no-annotation, no-output-schema tool of this complexity, the definition covers return contents, edge-case fallbacks, segmentation constraints and routing to siblings thoroughly enough that an agent can call it correctly without guessing.

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 a 3 is the baseline, but the description adds real meaning beyond the schema: caenCode must be exactly 4 digits and 2–3 digit codes are rejected (with the reason), caenCode and industry are mutually exclusive, industry accepts name/slug/id, and year affects only counts while percentiles stay on the reference year.

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 states a precise verb+resource: aggregated statistics for a Romanian market segment (industry or 4-digit CAEN code, optionally narrowed to a county), and enumerates the returned metrics. It explicitly contrasts itself against search_companies, list_industries, get_cpv_market and get_financial_health.

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?

It provides an explicit 'when to use' section with representative queries (median turnover in Cluj software, company formation/dissolution counts, market sizing) and a dedicated disambiguation block naming each sibling it should not be confused with, plus the reason. Nothing is left to inference.

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