Skip to main content
Glama

Rybárstvo.sk

Search rybarstvo.sk

search_site
Read-onlyIdempotent

Full-text search over the Slovak fishing portal: fishing waters ("revír"), rivers and lakes ("tok"), river basins ("povodie"), fish species, wildlife, guides, local SRZ organisations and competitions. Returns titles, URLs and short details. The query can be in any language of the site (Slovak, Czech, English, German, Polish, Hungarian, Ukrainian, Spanish, French, Romanian, Italian), e.g. "pike", "Hecht", "Danube"; diacritics are optional.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_site"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoLanguage of the answer: texts and page URLs in this language. sk = Slovak (original), cs = Czech, en = English, de = German, pl = Polish, hu = Hungarian, uk = Ukrainian, es = Spanish, fr = French, ro = Romanian, it = Italian. Use the language of the user. If omitted, the language of the input is used when it can be recognised, otherwise Slovak.
typeNoOptional result type filter: rev = fishing water, tok = river/lake, pov = river basin, fish = fish species, bio = wildlife and plants, guide = guide, mo = SRZ organisation, comp = competition, hub = waters by region, znec = water quality, disc = discoveries, post = article, page = other page.
limitNoMaximum number of results (default 8).
queryYesSearch text in any supported language, e.g. "Hron", "kapor", "carp", "Zemplínska šírava", "Waag", "hájenie šťuka".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / lang
      Added value: +{
      +  "description": "Language of the answer: texts and page URLs in this language. sk = Slovak (original), cs = Czech, en = English, de = German, pl = Polish, hu = Hungarian, uk = Ukrainian, es = Spanish, fr = French, ro = Romanian, it = Italian. Use the language of the user. If omitted, the language of the input is used when it can be recognised, otherwise Slovak.",
      +  "enum": [
      +    "sk",
      +    "cs",
      +    "en",
      +    "de",
      +    "pl",
      +    "hu",
      +    "uk",
      +    "es",
      +    "fr",
      +    "ro",
      +    "it"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / query / description
      Previous value: -"Search text, e.g. \"Hron\", \"kapor\", \"Zemplínska šírava\", \"hájenie šťuka\"."New value: +"Search text in any supported language, e.g. \"Hron\", \"kapor\", \"carp\", \"Zemplínska šírava\", \"Waag\", \"hájenie šťuka\"."
  2. Changed1 schema field changed
    • changedInput schema / properties / type / enum
      Previous value: -[
      -  "page",
      -  "fish",
      -  "bio",
      -  "guide",
      -  "disc",
      -  "mo",
      -  "pov",
      -  "tok",
      -  "rev",
      -  "hub",
      -  "znec",
      -  "comp",
      -  "post"
      -]New value: +[
      +  "page",
      +  "fish",
      +  "bio",
      +  "guide",
      +  "kb",
      +  "disc",
      +  "mo",
      +  "pov",
      +  "tok",
      +  "rev",
      +  "hub",
      +  "znec",
      +  "comp",
      +  "post"
      +]
  3. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. Beyond that the description adds genuinely useful behavior: it discloses the return shape (titles, URLs, short details) and that diacritics are optional and queries work across eleven languages. It does not explain ranking or ordering of results, which is a modest remaining gap.

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?

Two sentences, front-loaded with the core action and scope, then the return shape and query-language notes. The content-type enumeration is long but each item carries filtering information for the agent. Minor redundancy with the enum descriptions in the schema is the only waste.

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 a read-only search tool with no output schema, the description covers what is searched, what is returned, and how queries should be phrased, including the diacritics and language-fallback behavior. What it omits — result ordering and whether the `limit` cap reflects total truncation — are small gaps rather than blockers for correct invocation.

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 schema already documents all four parameters, setting the baseline at 3. The description nevertheless adds meaning beyond it: it names content categories in the site's own vocabulary (revír, tok, povodie) that orient the agent toward the `type` filter, and states that queries may be written without diacritics — a behavioral nuance about `query` that the schema does not encode.

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 and resource ('Full-text search over the Slovak fishing portal') and then enumerates the exact object types covered — waters ('revír'), rivers/lakes ('tok'), basins, fish species, wildlife, guides, organisations, competitions — which maps directly onto the enum domains. It also says what comes back (titles, URLs, short details), so an agent can distinguish it from the get_/list_ siblings at a glance.

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

Usage Guidelines3/5

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

Usage is only implied: the word 'search' plus the content-type list suggests this is the tool for keyword lookups across many entity types, while the siblings (get_water, list_articles) serve targeted lookups. However, no sibling or alternative is named and there is no explicit when-not guidance, so the agent must infer the routing boundary itself.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources