Skip to main content
Glama

kataster_lv_import

Parse saved Slovak LV extracts (HTML or PDF) and LV previews into structured parcel, owner and encumbrance data; batch several files or folders to get a summary per LV.

Instructions

Read LV extracts (výpis z LV, HTML or PDF) and LV previews (Náhľad LV, HTML) saved from the browser.

One file: returns the parsed LV: header (district, municipality, k.ú., date of data), part A (parcels with area, land type, location; codes translated by the legend; buildings in stavby with súpisné číslo, the parcel under the building, kind and the LV of the land), part B (owners with shares, acquisition titles, notes; administrators and tenants) and part C (encumbrances, ťarchy). A block of flats lists its units in jednotky (flat or non-residential premises, entrance, floor, share of the common parts) and each owner of a unit carries jednotka. zdroj_typ tells the input: vypis_lv_html, vypis_lv_pdf or nahlad_lv (the preview has no administrators/tenants section). A folder or several paths: a summary per LV (the same LV twice is merged: newer data, extract before preview), unreadable files are listed in varovania. Makes no network request. Results are kept in the local personal-data cache for 7 days (owner-only permissions on POSIX); kataster_osoba_prehlad reads them.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "kataster_lv_import"
  }
}

Input Schema

NameRequiredDescriptionDefault
htmlNoThe HTML itself, instead of a path.
pathNoSaved LV page or PDF, or a FOLDER with several of them.
pathsNoSeveral files or folders at once.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A4.6/5.0
Behavior5/5

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

No annotations are supplied, so the description carries the full burden and does so well: it discloses that no network request is made, that results are cached locally for 7 days with owner-only POSIX permissions, that unreadable files surface in varovania, that duplicate LVs are merged with newer-data/extract-before-preview precedence, and that previews lack the administrators/tenants section.

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 purpose, then organized into one paragraph per input mode, with no filler or repetition. It is dense — heavy on Slovak domain terms (výpis, jednotky, ťarchy) and output-field detail — but that density is doing real work given the absence of an output schema.

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

Completeness5/5

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

With no output schema and no annotations, the description compensates by describing the returned structure (header, parts A/B/C, stavby, jednotky), the zdroj_typ discrimination, error reporting, cache lifetime, and the downstream consumer. An agent has everything needed to pick the right argument and interpret the result.

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, but the description adds meaning beyond it: `path` may be a folder and `paths` a mix of files and folders, with multi-input invocations collapsing into a per-LV summary and merging duplicates. The three input modes (single file, folder, inline html) are also mapped to distinct return shapes, which the schema alone does not convey.

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?

Opens with a specific verb and resource: read saved LV extracts/previews (HTML or PDF) and return a parsed structure. The scope is bounded precisely by the 'saved from the browser' and 'Makes no network request' clauses, which implicitly separates it from the online lookup siblings, and it names kataster_osoba_prehlad as the cache consumer.

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?

Gives clear conditions for use: files saved from the browser, either a single file or a folder/multiple paths, with a stated distinction for preview inputs. It does not explicitly say what to do instead when the data is not on disk (e.g. 'use kataster_lv for a live lookup'), so the exclusion is left to inference.

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