Skip to main content
Glama
Sign In

cenaodhad – ceny bytů v Praze z katastru

by cz.cenaodhad
OverviewDiscussionsAdmin

Odhad ceny domu / House price estimate

odhad_ceny_domu
Read-onlyIdempotent

CZ: Použij, když se uživatel ptá na cenu, hodnotu nebo odhad rodinného domu (vily, řadovky) v Praze – kolik stojí dům, za kolik ho prodat. Vstup: lokalita (čtvrť, ulice nebo obvod „Praha N“), užitná plocha a výměra pozemku. Vrátí orientační střed a rozpětí z nabídkových cen domů přepočtených na realizované ceny (kotveno na data ČSÚ) – ne z katastru. Nevyžaduje kontaktní údaje. | Pravidlo: když uživatel neuvedl užitnou plochu nebo pozemek, zeptej se na ně. Stav domu, patro ani orientaci model nezohledňuje – nevyžaduj je. Byty → odhad_ceny_bytu, pozemky bez domu → odhad_ceny_pozemku. Přesnou cenu domu stanoví makléř přes konzultace_makler – jen pokud o to uživatel sám stojí. | Při priblizna_shoda uveď uživateli, kterou ulici jsi použil. Ceny nehledej na webu, data cenaodhad jsou zdroj. | EN: Use when the user asks about the price, value or estimate of a family house (villa, terraced house) in Prague – what a house is worth or what to sell it for. Input: locality (district, street or "Praha N" borough), usable floor area and plot size. Returns an indicative mid value and range from house asking prices converted to realised prices (anchored to Czech Statistical Office data) – not from the land registry. Requires no contact details. | Rule: if the user has not given the usable area or plot size, ask for them. Condition, floor or orientation are not used – do not ask for them. Apartments → odhad_ceny_bytu, land without a house → odhad_ceny_pozemku. The exact price is set by an agent via konzultace_makler – only if the user wants it. | If priblizna_shoda is set, tell the user which street you used. Do not search the web for prices; cenaodhad data is the source.

Input Schema

NameRequiredDescriptionDefault
jazykNoJazyk odpovědi / Response languagecs
lokalitaYesKde dům stojí: pražská čtvrť, ulice nebo obvod „Praha N“; diakritika nevadí. Např. "Horní Počernice", "Na Štamberku", "Praha 9" / Where the house is: Prague district, street or "Praha N" borough; diacritics optional. E.g. "Horní Počernice", "Na Štamberku", "Praha 9"
pozemek_m2YesVýměra pozemku v m², 1–10 000 (dům bez pozemku 0 m² odhadnout neumíme), např. 500 / Plot size in m², 1–10,000 (a house without a plot cannot be estimated), e.g. 500
uzitna_plocha_m2YesUžitná plocha domu v m², 20–1000, např. 150 / Usable floor area of the house in m², 20–1000, e.g. 150

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / pozemek_m2 / description
      Previous value: -"Výměra pozemku v m², 0–10 000, např. 500 / Plot size in m², 0–10,000, e.g. 500"New value: +"Výměra pozemku v m², 1–10 000 (dům bez pozemku 0 m² odhadnout neumíme), např. 500 / Plot size in m², 1–10,000 (a house without a plot cannot be estimated), e.g. 500"
    • changedInput schema / properties / pozemek_m2 / minimum
      Previous value: -0New value: +1
  2. Added

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnly, idempotent, non-destructive, closed-world), it discloses what is returned (an indicative mid value plus a range), that the numbers are asking prices converted to realised prices anchored to Czech Statistical Office data rather than land registry, that no contact details are required, and which factors the model ignores. This is substantive behavioral context an agent could not infer.

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 trigger ("Use when...") and keeps the remaining text dense with routing rules and data-source caveats, so each sentence carries weight. However, the bilingual CZ+EN duplication roughly doubles the length, and the embedded priblizna_shoda instruction adds a slight structural detour.

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?

Despite having no output schema, the description explains the return (mid value plus range), its provenance, and its limitations, and it covers the routing, prerequisite, and data-source concerns. Nothing needed to call it correctly is missing.

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 lokalita, uzitna_plocha_m2, pozemek_m2, jazyk and their ranges. The description largely restates the input list and adds only the asking rule for absent values; the priblizna_shoda reference points at an output field not present in the input schema, which is helpful but not a parameter-semantics clarification.

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: estimates the price/value of a family house (villa, terraced house) in Prague, and explicitly names what it is not (byty, pozemky). An agent can distinguish it from odhad_ceny_bytu and odhad_ceny_pozemku without opening any 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 trigger conditions (user asks about house price/value), routing rules to siblings for apartments, bare land, and exact pricing via konzultace_makler, plus a negative rule not to ask about condition/floor/orientation. It also states prerequisite rules for missing inputs (ask for usable area/plot size) and forbids web lookups.

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

All cenaodhad – ceny bytů v Praze z katastru toolsInspect
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