Search otwarteAPI.pl — a catalog of 53 official public Polish and EU APIs (VAT white list, KRS, GUS, NBP, ECB, Eurostat, VIES and more), curated for AI agents. One tool: find the right API by natural-language query. No API key, no signup.
Scored across 1 tool
There is only one tool, so there is no possibility of confusion or overlap between tools. An agent can unambiguously select 'szukaj_api' for any catalog search need.
The single tool name 'szukaj_api' follows a clear verb_noun pattern (search + API). With only one tool, there is no mixed convention or inconsistency to penalize.
A single tool for a read-only API catalog directory is slightly under the typical tool count but reasonable. The tool is comprehensive, covering both search and full-catalog retrieval through an empty query.
The tool fully handles the domain of searching and browsing a public API catalog, including filtering, jurisdiction, authorization type, and format. No additional lifecycle or update operations are relevant for this read-only directory use case.
Przeszukuje otwarteAPI.pl — katalog 92 oficjalnych, publicznych API rządowych z Polski, UE i kilkudziesięciu krajów (rejestry firm, VAT, statystyka, otwarte dane). Zwraca pasujące wpisy z linkiem do oficjalnej dokumentacji, jurysdykcją, typem autoryzacji i formatem. Puste zapytanie zwraca cały katalog (opcjonalnie zawężony filtrami).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maksymalna liczba wyników (1–92, domyślnie 8). | |
| temat | No | Tag do zawężenia, np. „firmy”, „dane-statystyczne”, „bez-klucza”. Opcjonalne. | |
| zasieg | No | Kod jurysdykcji do zawężenia, np. PL, EU, DE, GB, US. Opcjonalne. | |
| zapytanie | No | Zapytanie w naturalnym języku (PL lub EN), np. „sprawdź VAT firmy w Estonii” albo „company register Germany”. Opcjonalne. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and it does well: it discloses search scope (92 public APIs), result fields, and the empty-query behavior. It does not mention errors, rate limits, or whether the search is fuzzy/keyword-based, but for a read-only catalog search the key behavior is covered.
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?
Two sentences supply catalog identity, scope, return fields, and empty-query behavior without padding. The first verb states the action up front. The second sentence is slightly dense but all information 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?
There is no output schema溯, and description compensates by listing result fields (link, jurisdiction, auth type, format). All parameters are documented in the schemaijah; no prerequisites or auth mention needed since no annotations indicate them. The empty-query behavior rounds out the operational picture.
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?
Input schema covers all parameter semantics thoroughly (limit, temat, zasieg, zapytanie), so the description does not need to repeat them. The description adds a small amount of context by mentioning filters and natural language queries, which is enough to reach the baseline for high schema coverage.
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 opens with a specific verb ('Przeszukuje'/'searches') and names the exact resource (openapi.pl, a catalog of 92 official public APIs). It also states the concrete result fields (link, jurisdiction, authorization type, format), so an agent immediately knows what the tool does and what it returns.
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?
The description makes the tool's purpose clear and covers special behavior: an empty query returns the entire catalog, optionally narrowed by filters. It doesn't mention when to prefer an alternative, but there are no sibling tools to contrast against, so this is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
szukaj_api1 field changedInput schema / properties / limit / descriptionPrevious value: -"Maksymalna liczba wyników (1–60, domyślnie 8)."New value: +"Maksymalna liczba wyników (1–92, domyślnie 8)."szukaj_api1 field changedInput schema / properties / limit / descriptionPrevious value: -"Maksymalna liczba wyników (1–53, domyślnie 8)."New value: +"Maksymalna liczba wyników (1–60, domyślnie 8)."szukaj_api
