Find Czech companies by CZ-NACE activity code (economic sector classification). Example: "62" = IT, "47" = retail, "86" = healthcare. Optional city filter. Useful for market research.
| Name | Required | Description | Default |
|---|---|---|---|
| city | No | Optional city filter. | |
| nace | Yes | CZ-NACE code, 2-6 digits (e.g., "62" for IT, "62010" for programming services). | |
| pocet | No | Max results. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds the NACE code examples and optional city filter, but does not disclose return format, pagination, or any edge-case behavior. This is acceptable but minimal beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, front-loaded with the core purpose, followed by useful examples and a use-case line. No wasted words; each sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read-only search tool with full schema coverage and annotations, the description is adequate. It explains the key search dimension (NACE) and optional filter, and the title/annotations confirm read-only and open-world behavior. It doesn't specify return fields, but the lack of an output schema makes this a minor gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds a few extra NACE examples and mentions the optional city filter, but these largely duplicate schema info. It doesn't fundamentally extend parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Find') with a clear resource ('Czech companies') and a precise scope ('by CZ-NACE activity code'). It distinguishes from sibling tools like search_by_address and lookup_by_ico by focusing on the NACE classification, and the examples ('62'=IT, '47'=retail) reinforce the purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly states a use case ('Useful for market research') and implies the tool should be used when filtering by economic sector. It doesn't mention alternatives or exclusions, but the context is clear enough for an agent to choose this over a generic company search.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct aspect of Czech company data: VAT status, bank accounts, historical changes, statutory bodies, basic lookup by IČO, address search, NACE search, combined search, DIČ validation, and monitoring. No significant overlap.
All tools use consistent snake_case and follow a verb_noun pattern (e.g., check_vat_payer, get_statutaries, search_companies). No mixing of conventions.
10 tools is appropriate for the domain of Czech company information, covering lookups, searches, VAT checks, history, and monitoring. Not excessive nor insufficient.
Core operations for the ARES domain are covered: lookup, search, VAT and DIČ checks, history, and statutory data. The watch_entity tool is a stub, and there might be missing advanced queries, but the set is largely complete for intended use.