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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, but the description adds real behavioral context: it rechecks authoritative stay totals and refuses price/quote data, renders only once, caps at 3 properties / 4 cards per page / 60 offers, and enumerates what it will never do (bookings, holds, quotes, emails, payments). Some of this is workflow narration rather than behavior, which keeps it from a clean 5.

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?

Every sentence carries information — limits, exclusions, sibling routing — and the when-to-use condition leads. However it is a dense run-on with mild redundancy ('Render once' is restated as 'show_available_rooms renders once') and a typo ('Up to3 properties') that slightly impede scanning.

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 a complex nested-object tool with an output schema (so return values need no explanation), the description covers workflow ordering, caps, sibling routing and hard exclusions. The only gap is the offset parameter and how first-page vs. paginated rendering is bounded, which is only handled indirectly via the sibling reference.

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 25%, so the description must compensate, and it does: it maps the caller's obligations to selections (property/room/rate/count IDs), exact dates, guests, budget and display currency. The offset/pagination parameter is not addressed here (it is delegated to the sibling), so coverage is strong but not complete.

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+resource — a read-only visual room-comparison presentation that renders once — and explicitly differentiates itself from the sibling get_available_room_cards ('data-only for mounted-card pagination'). The core purpose is front-loaded but wrapped in workflow phrasing ('Default visual presentation after the final useful availability comparison...'), so it takes parsing to extract the plain 'what it does'.

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 preconditions (after the final useful availability comparison, when UI is supported, when text-only was not requested) and explicit exclusions (no photo request needed, no repeat searches or widgets). It names the alternative sibling and the condition that selects it: get_available_room_cards for mounted-card pagination, plus a stated ordering dependency on search_property_availability.

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