Skip to main content
Glama

Ask Gozatu! (FAQ answers)

ask_gozatu
Read-onlyIdempotent

Short, sourced answers (German) from more than 2,600 questions and answers in Gozatu! articles about San Sebastián and the Basque Country: food and drink, customs, prices, transport, beaches, festivals, individual bars and restaurants. Ask in German for best results. Each answer comes with the article it is taken from.

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": {
      "question": "<question>"
    },
    "name": "ask_gozatu"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoNumber of answers (default 3, maximum 8).
questionYesThe question, e.g. "Was ist eine Gilda?" or "Wie viel Trinkgeld gibt man in San Sebastián?".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, closed-world and non-destructive, so the safety profile is settled. The description adds non-obvious behavior beyond that: answers are language-sensitive (German best), short, and each is attributed to its source article — sourcing that an agent would otherwise not know to expect.

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-loads the payoff (short, sourced answers) and then qualifies scope, language and provenance in two further sentences with almost no filler. The mid-sentence topic list is dense but functional; nothing extraneous remains.

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?

With no output schema, the description carries the burden of describing returns and does so by stating each answer arrives with its source article. For a two-parameter read-only lookup, the remaining gap is only the absence of explicit fallback guidance when the FAQ corpus has no matching answer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so question and limit are already documented, and the description rightly does not restate the limit range. It adds one piece of real semantic value beyond the schema — that the question should be phrased in German for best results — but gives no guidance on how to phrase a question to hit the corpus well.

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?

Names a concrete verb and resource (short, sourced answers from Gozatu! Q&A articles) and enumerates the topical scope: food, customs, prices, transport, beaches, festivals, venues. An agent can tell this is a curated FAQ answer lookup rather than a general web search, which separates it from siblings like search or fetch.

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?

The topical scope (San Sebastián and the Basque Country) plus the language instruction imply when this tool is the right choice, and the FAQ-corpus framing hints at question-shaped queries. However, it never states when NOT to use it or names an alternative such as search or trip_check, leaving the routing decision to inference.

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