LivinIsto CZ

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

Annotations only cover read-only/idempotent/no-destruction, but the description adds substantive behavior: asking prices vs actual sale prices, the 8-listing minimum sample rule, monthly figures for rent, and the found: false contract distinguishing an unknown place from a too-sparse one (never a national fallback). This is meaningfully beyond what the structured fields disclose.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense and front-loaded with the usage trigger, then return semantics, then caveats and exclusions. Every clause carries information (thresholds, rent cadence, found: false), though the single long paragraph is heavier than it needs to be.

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

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

For a statistical lookup with an output schema, the description covers everything an agent needs: trigger, caveat framing ('a guide'), sample-size floor, the missing-data contract, and exclusions. Return-value structure is deferred to the output schema, which is correct.

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

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

Schema description coverage is already 100%, so the baseline is 3, but the description adds effect-level meaning: supplying a layout also returns the median of today's comparable listings, and the rent transaction yields monthly figures. It stops short of explaining propertyType choices (e.g. pozemek/apartman), so it is above baseline rather than exhaustive.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: returns the median ASKING price per m² of a Czech municipality from LivinIsto's monthly index, optionally extended by layout. This is clearly distinct from get_property_details (a specific property) and search_properties (finding listings), since it is an aggregate statistic and the description frames it that way.

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

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

Gives explicit trigger conditions ('when the user asks how much homes cost per square metre... or whether a price per m² is reasonable') and explicit exclusions ('Do not use it to value a specific property's condition, for commercial property or for places outside the Czech Republic'). The when/when-not pair is about as complete as this class of tool needs.

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

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

Annotations already cover the safe-read profile (readOnly, idempotent, non-destructive), yet the description still adds substantive behavior: what is deliberately NOT returned (agent/seller name, phone, e-mail, listing description, source URL) and the miss case ('found is false' when the listing left the offer). That is exactly the kind of negative/boundary disclosure annotations cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the usage trigger and tightly packed — every clause carries information (scope, precondition, exclusions, miss case). It is dense rather than bloated, though the long parenthetical field list and multi-clause final sentences make it heavier than an ideal single-pass read.

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

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

For a one-parameter lookup with an output schema already defining return shape, the description supplies everything an agent needs: invocation source for the id, scope of returned facts, explicit omissions, and the failure signal. No gaps remain that would cause a mis-call.

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

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

Schema description coverage is 100% for the single propertyId parameter, so baseline is 3, but the description adds real meaning beyond the schema: the id must originate from search_properties results and must not be guessed. It stops short of format examples or validation behavior, so it is above baseline but not maximal.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('more about one specific home returned by search_properties') and enumerates exactly what detail is covered (floor, condition, construction, ownership, energy class, balcony, lift, parking, price history). This clearly separates it from get_price_per_m2 and search_properties without needing the schema.

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

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

Gives an explicit trigger ('when the user asks for more about one specific home returned by search_properties'), a precondition ('Requires the property id from search_properties; do not guess ids'), and routes the out-of-scope contact need to an alternative ('the user opens the listing's url'). Nothing 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.

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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, openWorldHint=false, destructiveHint=false), so the description is free to add the traits annotations cannot express: at most 6 unrecognised words get matched in listing text, extras are returned in notUnderstood, up to 10 results, and relaxed criteria are reported when nothing matched exactly. This is unusually rich disclosure for a search tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the when-to-use trigger, then query mechanics, then limits and return behaviour — a logical order with no filler sentences. It is long for a one-parameter tool, and the Czech-language examples plus the 6-word rule could be tightened, but each sentence carries actionable information.

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

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

Even though an output schema exists and return values need not be explained, the description covers what an agent needs end-to-end: query format, language, limits, exclusions, result cap, and how unparsed input is surfaced (notUnderstood/matchedInText). Nothing required to call this correctly is missing.

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

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

Schema coverage is 100% for the single 'query' param, yet the description still adds real semantics beyond the schema: pass criteria as ONE short phrase, in Czech (Slovak accepted), with numbers as the user said them, omitting filler words like hledám/prosím. The worked examples ('byt 2+kk Praha do 6 milionů') show the expected string shape far better than the schema's single example.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (search) and resource (homes for sale or rent), plus a precise scope: Czech Republic, flats/houses/cottages/plots, by layout, town, district, price, floor area or features. An agent can immediately tell this apart from get_property_details and get_price_per_m2, which are single-property/price-analytics tools.

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

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

Opens with an explicit when-to-use trigger ('Use this when the user wants to find a home for sale or rent...') and closes with an explicit when-not list: no commercial property, garages, holiday stays or property abroad. It also states the freshness caveat ('the offer changes daily, so a home may already be gone'), which tells the agent to expect stale results.

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