Say which people on a shared trip an item is for — one person's separate flight, one person's room. Omitting travelers (or passing an empty list) means everyone, which is the default and right for most items.
| Name | Required | Description | Default |
|---|---|---|---|
| item_id | Yes | ||
| item_type | Yes | ||
| travelers | No | Member user ids this is for (from list_journey_members). Omit for everyone — that's the norm. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate a non-read-only, idempotent, non-destructive tool, and the description adds useful behavioral context: omitting travellers or passing an empty list means everyone, with everyone being the common case. It does not mention overwriting existing assignments or prerequisites, but the idempotent annotation reduces some of that need.
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 two tight sentences with no filler. It front-loads the core action and immediately gives the most important behavioral default, making it easy for an agent to parse.
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 simple setter with no output schema, the description covers the essential behavior and default, while the schema supplies the enum values and traveler-source guidance. It could explicitly mention that this modifies an existing item, but the sibling create/update tools and tool name make that reasonably inferable.
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 33%, but the description adds meaningful semantics for the travelers parameter, including empty-list behavior and the default-to-everyone rule. It provides little meaning for item_id or item_type beyond what the enum values themselves show, so it only partially compensates for the low schema coverage.
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 gives a concrete outcome ('say which people... an item is for') with helpful examples like 'one person's separate flight, one person's room.' It clearly identifies the resource (item travellers) but does not explicitly state 'assign' or 'update' and does not distinguish itself against sibling tools.
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 tells the agent when subsetting travellers is appropriate by explaining that omitting them means everyone, and that everyone is the default for most items. It does not name alternative tools or state exact when-not-to-use conditions, so it falls short of a 5.
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.
Each tool targets a distinct resource and action (e.g., create_flight vs create_activity vs create_stay), and descriptions clarify overlaps like stay vs accommodation. The only potential confusion (create_activity covers travel legs) is explicitly explained, so misselection is unlikely.
All tools follow a consistent verb_noun pattern using standard verbs: create, delete, get, list, search, set, update, add, remove, leave. Nouns are consistently singular and descriptive (passport, journey, stay, flight, accommodation). No mixed conventions or vague verbs.
With 36 tools, the count is higher than typical, but the server covers a wide domain: journeys, stays, activities, flights, accommodations, visas, documents, preferences, and sharing. Each entity has CRUD operations plus search and status, so the count is justified, though bordering on heavy.
The tool surface is remarkably complete: full CRUD for every entity (journeys, stays, activities, flights, accommodations, visas), user profile access (get_me), search utilities, sharing controls (join links, member management), and preferences. No obvious dead ends or missing lifecycle steps; even edge cases like deleting bookings before stays are handled.