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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds meaningful behavioral limits beyond annotations: results are suggestions near the port, not verified time-ashore matches or live availability; prices are indicative and not cruise fares; affiliate URLs must be preserved; reviews/protected content and widgets are excluded.

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 front-loaded with the core action and on-demand condition, and most sentences add concrete constraints. It is a dense single paragraph, and fragments like "No widget" are terse enough to be slightly underspecified rather than maximally clear.

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?

For an external search tool with no output schema and no schema parameter descriptions, the definition covers key invocation rules and important output caveats. It still omits explicit response-shape guidance and direct page-parameter behavior, leaving minor gaps.

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 0% schema description coverage, the description must carry parameter meaning. It explains portId provenance, date as the port visit date, and q as activity keyword search preserved across pagination, but page is only indirectly mentioned through pagination and lacks direct semantics.

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 and resource: "Search Viator" for "activities or excursions" at a port. It also distinguishes the port-ID source siblings list_excursion_ports and get_sailing, though it does not explicitly differentiate this search from get_excursion or present_excursions.

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?

It gives explicit usage conditions: search only on demand when the user asks for activities/excursions. It also names where to get portId, clarifies that date must be the port visit date rather than the cruise departure date, and explains preserving q across pagination.

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