Return ATA stays assigned to a published building, optionally filtered by live dates and guest counts.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | ||
| adults | No | ||
| checkIn | No | ||
| checkOut | No | ||
| children | No | ||
| priceAudience | No | ||
| displayCurrency | No | Optional 3-letter currency for approximate traveler-facing display conversion. Native property currency remains authoritative. | |
| internalAgentKey | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds minor context like 'published building' and filtering options, but does not elaborate on error handling, pagination, or what 'ATA stays' precisely means.
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?
Single sentence, no unnecessary words. Efficient but could be slightly more structured to separate purpose and optional filters.
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?
Lacks details on return format, error conditions, or behavior for missing buildings. With 8 parameters and no output schema, the description is too minimal to be fully complete for an AI agent.
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 low (13%), so the description must compensate. It mentions 'live dates' and 'guest counts' which map to checkIn/checkOut and adults/children, but ignores other parameters like priceAudience, displayCurrency, and internalAgentKey. Adds partial value.
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 clearly states the action ('Return'), the resource ('ATA stays assigned to a published building'), and optional filters ('live dates and guest counts'). It effectively distinguishes this tool from siblings like search_buildings or search_property_availability.
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?
No explicit guidance on when to use this tool versus alternatives. The description implies it is for retrieving stays for a specific building, but does not mention when not to use it or suggest sibling tools for other scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Multiple search tools (search_buildings, search_property_catalog, search_network_availability) and detail tools (get_building_details, get_property_details, get_stays_in_building) have overlapping boundaries, though descriptions clarify date and availability distinctions. The verification/handoff tools are more clearly separated but still numerous.
All tools follow a consistent snake_case verb_noun pattern (create_*, get_*, search_*, start_*, verify_*). There are no mixed casing conventions or vague generic verbs, making the set predictable and easy to scan.
With 22 tools, the server is on the heavy end of a typical MCP scope, though each tool has a defined purpose. Several narrow status and discovery helpers inflate the count, but the overall count is not yet extreme.
The booking lifecycle is incomplete: create_quote and create_provisional_booking exist, but there is no cancel, update, or explicit payment action, and get_reservation_status explicitly cannot change or cancel a reservation. Search and verification are well covered, but missing booking mutations will cause agent dead ends.