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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds real context: facts without forecasts, exact counts but no company names, output delivered as a web page plus PDF, and an explicit boundary that the report neither scores the location nor predicts revenue. Missing are latency, cost, and what happens for unsupported addresses.

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?

The purpose is front-loaded, but the text is an unusually dense run-on that packs output-field details (`opis_miejsca`, `galeria`) and many parenthetical caveats into one Polish sentence followed by a compressed English gloss. Substantive but hard to scan.

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?

With no output schema, the description carries the burden of describing return content and does so thoroughly: competitor counts, walking/driving reach times, zoning articles, GUS overnight-capacity data, opening hours of neighbours, and links to the page and PDF. Only delivery mechanics (format, latency, failure modes) remain unspecified.

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% and both parameters are documented there, including industry synonyms and accepted place formats (address, parcel, coordinates, dz:/bud:/pkt:, report URL). The description reinforces this with industry examples but adds no syntax or constraints beyond the schema, so the baseline 3 applies.

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?

The description names a specific resource (an IleM² business location report) and scopes it precisely: competitors within 500 m, residents in reach, transit, zoning, closure rates, construction, plus links. It does not distinguish this from the sibling `raport` (general report) or `ceny_obszaru`, so the agent must still guess between overlapping siblings.

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?

Usage is implied rather than stated: it applies to 'miejsce i branża' and explicitly refuses to evaluate the site or forecast turnover, which softly signals that `szacunek_*` tools handle valuations. No alternative is named and no prerequisites (cost, wait time, data availability) are given.

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