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

Adds substantially beyond readOnlyHint/openWorldHint: results are computed locally from a large underlying list (Warsaw ~1.3 MB, so calls can take seconds), figures may differ from the site's own totals, prices are asking not transaction prices, and it defines the STOP-error protocol plus the rule that _url fields go to the user as links. Minor deduction only because the RCN/price-family enumeration and STOP paragraph are boilerplate repeated across the tool family rather than tool-specific.

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 correctly — purpose first, then result fields, then limits and behavioral caveats. But it is a dense block that spends sentences on sibling tool lists for price-type separation and on a generic STOP-handling paragraph that is not specific to this tool, so it is longer than this tool alone requires.

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 read-only, open-world, six-parameter filter tool with a full output schema, it covers everything an agent needs: required city source, optional filters, what is excluded (archived offers, multi-city), latency expectations, and the shape of an empty result via the hint field.

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%, so the baseline is 3; the description still adds meaning by framing the price/area parameters as an optional narrowing filter on the offer set and by tying top_developers to the returned list. It does not add units or default details beyond the schema, so it stays just above baseline.

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?

Opens with a specific verb+resource+scope: statistics of the developers' offer market in one city, then enumerates exactly what is returned (offer/investment/developer counts, price/price-per-m²/area distributions, top developers). It explicitly contrasts with sibling tools ('not about particular flats') and names the cross-cutting price-type boundary with the transaction 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?

Explicit when-to-use ('city's market — typical prices, who has the most offers'), when-not-to ('not about particular flats'), and which siblings belong to which price family. It also names prerequisites (city_slug from deweloperuch_search_locations) and exclusions (active offers only, one city only, polska does not work).

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