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

Annotations already provide readOnlyHint, idempotentHint, and openWorldHint, but the description adds valuable behavioral context: 'Up to 20 results, cursor tied to filters' and 'No results means no matches; do not widen filters without asking.' This directly supports the open-world hint and guides agent behavior beyond structured annotations.

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?

Four tight sentences, each earning its place: scope, required constraints, pagination behavior, and no-match guidance. The most important usage information is front-loaded immediately after the purpose statement.

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 14 parameters without an output schema, the description covers the critical constraints needed to invoke the tool correctly. It explains result limits, cursor pagination, and required dependencies, though it does not describe the return value shape or mention all optional parameters.

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?

With schema description coverage at only 21%, the description must compensate, and it does for key dependencies: purpose is required, municipality requires district, and rent_period is required with rental budgets. It also clarifies that cursor is tied to filters. However, it does not elaborate on several other parameters, leaving some semantics to schema names and enums.

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: 'Search currently published properties in Portugal by exact structured filters.' The scope (currently published, Portugal) and method (exact structured filters) clearly distinguish it from siblings like get_property, compare_properties, and get_area_statistics.

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 usage context and constraints: purpose is required, municipality requires district, rental budgets require month/week/night, and results are capped at 20 with cursor tied to filters. It also tells the agent not to widen filters without asking, but it does not explicitly route to alternatives like get_property or compare_properties.

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