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

With annotations already covering readOnly, openWorld, idempotent, and non-destructive hints, the description adds valuable behavioral context beyond them: results include test records, availability is not independently verified, geographic filters describe a search area rather than a precise address, and pagination must reuse the nextCursor with unchanged filters. These details meaningfully shape how an agent should interpret and invoke the tool.

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 description is four sentences with no filler. The core usage trigger is front-loaded, followed by market-specific, geolocation, pagination, and data-quality caveats. Every sentence adds operational value.

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?

Given the tool's complexity with 27 parameters, nested objects, and an output schema, the description provides strong contextual grounding: when to use it, how to handle locations, how to paginate, and what caveats to communicate. It could be even more complete by pointing to get_locations_autocomplete for resolving ambiguous locations, but as a whole it is sufficient for an agent to use the tool correctly in most cases.

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 description coverage is only 4%, so the description carries a heavier burden. It explains the meaning of key categories like location, budget, rooms, amenities, targetMarket, and cursor pagination, which maps to several parameters. However, with 27 parameters and nested objects, many individual fields such as polygon, bbox, radius, areaMin/Max, floorMin/Max, and the various amenity booleans are not semantically clarified in the description.

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 states a specific verb ('search') and resource ('public properties on nekretninenaprodaju.rs') and enumerates the main search criteria: location, budget, rooms, amenities. It clearly distinguishes the tool's purpose from siblings like get_property_by_slug or compare_properties, even though those alternatives are not named explicitly.

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 description gives explicit usage guidance: 'Use this when the user wants public properties...', instructs to use targetMarket RS for Serbia, advises resolving ambiguous locations first, and defines pagination behavior. It provides indirect when-not guidance by saying never to request GPS or a home address, but it does not explicitly name sibling tools as alternatives.

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