tvrtke

search_companies

Search and discover Croatian companies in the Sudski Registar using flexible filtering criteria such as partial/fuzzy name, street address, house number, house sub-number (podbroj), city, county (županija), inception date range, NACE/NKD industry activity code prefix, legal status, or legal proceedings (e.g. likvidacija, stečaj). Returns up to 50 matching records with basic entity profile summaries. RULES: Never invent company names, addresses, or filters. If search criteria are empty, interview the user with clarifying questions before calling this tool.

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": "search_companies"
  }
}

Input Schema

Name	Required	Description
`city`	No	Optional city of the company
`name`	No	Optional name of the company (fuzzy search)
`county`	No	Optional county (županija) of the company
`status`	No	Optional status (e.g., active, brisan, likvidacija)
`street`	No	Optional street name (e.g., Ilica, Radnička cesta)
`nkd_code`	No	Optional NKD code (e.g. 62.01)
`proceeding`	No	Optional legal proceeding / status (e.g., likvidacija, stečaj)
`house_number`	No	Optional house number (e.g., 10, 25)
`house_subnumber`	No	Optional house sub-number / podbroj (e.g., A, B, 1/2)
`inception_date_to`	No	Optional upper bound for company inception/foundation date (inclusive, format: YYYY-MM-DD or YYYY)
`inception_date_from`	No	Optional lower bound for company inception/foundation date (inclusive, format: YYYY-MM-DD or YYYY)

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 21, 2026

TDQS

A4.3/5.0

Behavior4/5

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

With no annotations, the description carries the full behavior burden and does useful work: it discloses the 50-record result cap and that results are only basic profile summaries, plus operational rules about not fabricating filters. It stays silent on pagination beyond the cap, ordering, and any auth/permission requirements, which are real gaps for an 11-parameter query tool.

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?

Front-loaded with purpose, then filters, then return shape, then rules — a sensible ordering with no filler sentences. The long filter enumeration largely restates schema parameters, which is mildly redundant but justifiable as a routing aid.

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 an 11-optional-parameter search tool with no annotations and no output schema, the description covers purpose, filter semantics, result cardinality, and an important interaction rule. Remaining omissions (what to do when the 50-record cap is hit, result ordering) are minor but real.

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 adds semantics the schema does not: name matching is 'partial/fuzzy', NKD/NACE matching is by industry code prefix, and the date range is an inception/foundation window. It also groups the filters into recognizable facets (address components, proceedings), which helps an agent pick the right parameter.

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?

States a specific verb (search and discover) and a precisely scoped resource (Croatian companies in the Sudski Registar), then enumerates the filterable facets, which tells an agent immediately that this is the broad discovery tool rather than one of the get_company_* detail siblings. The stated return of 'basic entity profile summaries' further separates it from the richer per-entity tools.

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

Usage Guidelines4/5

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

Gives an explicit precondition and when-not: if search criteria are empty, interview the user with clarifying questions before calling, and never invent filters. It stops short of naming alternatives (e.g., search_financial_screener for financial queries), so routing between the three search siblings 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 tvrtke tools Inspect

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

Need Help?