Poland Building Permits API – Pozwolenia na budowę (GUNB)

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

Goes well beyond the readOnlyHint/openWorldHint annotations: discloses the APIFY_TOKEN requirement, that each call starts one paid Actor run billed pay-per-event (named-organisation investors cost more), the 300 s wait, and that onlyNew merely stores a stateKey memory in the caller's own Apify account. It also clarifies the privacy rule that private-person investors are never named, which affects result interpretation.

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?

Two long sentences, but front-loaded with what is returned before constraints, cost, and output shape. Some detail (billing breakdown, 256 KiB cap) is dense but each clause carries operational weight; slight over-packing in sentence two costs it a point.

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 17-parameter, zero-required scraping tool with no output schema, the description still supplies the return contract ({items, truncated}, at most maxItems up to 100 and 256 KiB), cost model, timeout, and auth requirement. Nothing an agent needs in order to invoke it 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%, so the baseline is 3; the description adds value by summarising the implicit default (Mazowieckie unless voivodeships/TERYT set) and the investor-naming caveat that governs investorTypes/investorContains/onlyWithInvestor. It does not restate the per-parameter interaction rules already in the schema (e.g. daysBack vs dateFrom), so it adds context rather than duplicating.

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: returns building permit decisions (pozwolenia na budowę) and construction notifications (zgłoszenia) from the official GUNB RWDZ register, and enumerates the fields returned (project name, category, cubature, location, dates). It also names the sibling tool it is not (polish-land-parcels-uldk-zoning) for parcels/zoning, so an agent can route without opening either 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 explicit when-to-use ('construction projects and leads') and when-not ('for parcel boundaries and zoning use polish-land-parcels-uldk-zoning'), plus the geographic default behaviour (Mazowieckie first run, ALL or TERYT codes for others). Nothing essential 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.