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

Annotations already establish read-only, idempotent, non-destructive, and notably openWorldHint=false. The description adds the domain constraint (Croatian places only) and the fact that inflected grammatical cases are accepted, which the agent could not infer from annotations alone.

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 sentences, no padding, with the domain scope front-loaded and the usage rule immediately after. Every clause carries 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?

An output schema exists, so return values need no elaboration, and both input modes are covered. The only gap is behavior on ambiguous or unmatched names (multiple candidate towns, no result), which the agent would have to discover at runtime.

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 earns an extra point by making the mutually-exclusive usage pattern explicit (name OR lat+lon), which is not obvious from a zero-required-parameter schema that simply marks lat/lon as "or a point".

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 (resolve) plus resource (Croatian place name), and explicitly covers both directions of the mapping: name -> coordinates/kind/county and lat/lon -> nearest town. This is far more specific than the sibling tools, none of which do geocoding.

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?

"Use when the user names a place and you need coordinates, or to tell a user where coordinates are" gives clear triggering conditions for both modes. It does not name an alternative tool or state exclusions, but no sibling overlaps this function, so the guidance is adequate without them.

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