Skip to main content
Glama

kataster_osoba_navod

Guides you step by step through searching the official ESKN portal for a person’s parcels in one cadastral unit and saving LV previews to a folder for import.

Instructions

Guide (navod) for finding the parcels of a person in ONE k.ú. in the official ESKN search, by the user.

The server never searches by person and makes no network request here: the user searches in the browser (the portal's invisible CAPTCHA lets a person through), opens the LV previews, saves them into one folder, then kataster_lv_import reads the folder and kataster_osoba_prehlad builds the overview. The search is per k.ú., not per municipality: a town can have several k.ú. (ine_ku_obce) and a property "in village X" can lie in a neighbouring village's k.ú.; repeat the guide for every k.ú. that matters. Walk the user through the steps ONE AT A TIME (wait until a step is done), do not paste the whole list.

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": {
      "ku": "<ku>"
    },
    "name": "kataster_osoba_navod"
  }
}

Input Schema

NameRequiredDescriptionDefault
kuYesCadastral unit (k.ú.): name or 6-digit code.
icoNoIČO of the legal person.
typNoNatural person (fyzická) or legal person (právnická).fyzicka
menoNoFirst name (natural person).
nazovNoName of the legal person.
priezviskoNoSurname (natural person).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the burden well: it discloses that the work happens in the user's browser, that a CAPTCHA is involved, that no network request is made server-side, and that the agent must wait for each step. It does not say what the tool itself returns (a step list?) or how the guide state is tracked across calls, which is the 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?

Front-loaded with the core purpose and scoped with the negative statement before the procedural details; nearly every sentence carries new information. Slightly long with some repeated framing around k.ú. scope, but no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Strong on process, prerequisites and hand-off to sibling tools, but for a six-parameter guide tool it omits what the call actually produces and how the person fields (typ, meno, nazov, ico) affect the guide steps. An agent knows when and how to start the flow but not what to expect back.

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 description coverage is 100%, so the schema already documents ku, typ, meno, priezvisko, nazov and ico. The description adds meaning only for ku, reinforcing that cadastral unit granularity (including ine_ku_obce) is the key dimension, and says nothing about the person-identification parameters.

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 — a guide for finding a person's parcels in ONE k.ú. via the official ESKN search, performed by the user. It explicitly contrasts with the server-side siblings (kataster_lv_import, kataster_osoba_prehlad), so an agent can separate this from the actual search/import tools without opening a schema.

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

Usage Guidelines5/5

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

Gives explicit when-to-use framing, states what the tool does NOT do (server never searches, makes no network request), and names the follow-on tools in order. It also calls out the repetition condition (repeat per k.ú., not per municipality) and the interaction pacing rule (one step at a time).

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