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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is fully covered by structured data. The description adds that a result places the point on a parcel map and exposes a municipality plus an InfoGrunt.pl link, which is mild extra context beyond annotations but largely repeats what the output schema can 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?

Two short sentences, front-loaded with the search scope before the output description, with no filler. The second sentence partly duplicates what the output schema already conveys, which costs one 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?

With a rich annotation set and an existing output schema, the description only needs to cover the input contract and routing, and it covers the input format by example. The missing piece for a catalog of six geospatial siblings is routing guidance: nothing tells the agent to use this for addresses/towns and the find_parcel family for cadastral parcels.

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?

The single 'query' parameter has 0% schema description coverage, so the description carries the burden. The worked example 'Polna 5, Wieliczka' usefully demonstrates that 'street number, town' is an accepted format, but nothing is said about the 2–200 character bounds, whether a country qualifier is needed, or how partial or ambiguous names are resolved.

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 verb (Znajdź) and a specific resource class (adres, ulica, miejscowość), which is distinguishable from the parcel-oriented siblings like find_parcel and find_parcel_at_point. It stops short of explicitly stating that it does NOT search parcels, so the differentiation is inferable rather than declared.

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?

The example 'Polna 5, Wieliczka' implies the intended use case (geocoding a free-text location in Poland), so usage is implied. However, no sibling is named and there is no guidance on when to pick this over find_parcel or find_parcel_at_point, which are plausible alternatives for a user asking about a place.

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