AutoIsto CZ — car watch

Search cars AutoIsto CZ offers today

intent_search_offers

Read-onlyIdempotent

Use this when the user wants to find a used car for sale in the Czech Republic now. Pass what they are looking for as one short phrase (Czech or Slovak works best), e.g. "toyota rav4 hybrid do 600000 Kč". Returns up to 20 cars from AutoIsto CZ's offer in its own order, each with a link to the car on www.autoisto.cz, plus what was understood, which words were not applied and what had to be relaxed. When suggestIntent is true (nothing or little found, or part of the phrase was dropped), offer the user intent_publish_intent with the same statement so AutoIsto CZ keeps watching. Results come from listings AutoIsto CZ aggregates from the Czech market and may be incomplete; no seller contact is returned.

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": {
      "statement": "<statement>"
    },
    "name": "intent_search_offers"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No	At most this many cars (default 10; AutoIsto CZ returns at most 10).
`statement`	Yes	What the user is looking for, e.g. "suv automat do 500000 Kč".

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 28, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the read-only/idempotent annotations, it discloses result cap and ordering ('up to 20 cars ... in its own order'), payload contents (link, parsed understanding, dropped words, relaxations), and an important limitation: listings are aggregated and may be incomplete, with no seller contact returned. This is exactly the kind of context annotations cannot carry.

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 the usage trigger, then semantics, then return shape, then fallback routing — each sentence adds information. The final sentence about aggregated listings and no seller contact is slightly apart from the flow but still earns its place.

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 takes on explaining return values and does so substantively, plus data-provenance caveats. The one unresolved gap is the undefined 'suggestIntent' signal, which an agent needs to actually branch on; the untouted limit ceiling in the schema (max 10 in practice vs. maximum 20) also goes unflagged.

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; the description adds real guidance by telling the agent to pass one short phrase, that Czech or Slovak works best, and by giving a well-formed example. The limit parameter is not discussed at all, so the addition is partial rather than complete.

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 with scope: find a used car for sale in the Czech Republic now, sourced from AutoIsto CZ. It is clearly distinguishable from the intent_* siblings because it is the only search tool, and intent_publish_intent is explicitly named as the follow-up.

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?

Opens with an explicit trigger condition ('when the user wants to find a used car for sale in the Czech Republic now') and routes to intent_publish_intent under a stated condition. The routing condition depends on a 'suggestIntent' flag that is not a declared parameter and is never defined as a returned field, leaving the agent slightly unsure where that signal comes from.

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

All AutoIsto CZ — car watch 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?