Create a new trip
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Trip name (e.g., "London Christmas 2026") | |
| endDate | Yes | End date (YYYY-MM-DD) | |
| currency | No | Currency code (USD, GBP, EUR) | USD |
| timezone | No | Timezone (e.g., "Europe/London") | UTC |
| startDate | Yes | Start date (YYYY-MM-DD) | |
| budgetTotal | No | Total budget | |
| destination | Yes | Destination city/country |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint=false and destructiveHint=false, so the description adds nothing beyond what structured data conveys. It discloses no behavioral traits such as whether duplicate names are rejected, whether the trip is created empty, or what the response contains. The description is consistent with the annotations but provides no additional behavioral context.
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 four-word description is technically lean with no wasted words, but it is concise at the expense of substance — every word essentially restates the tool name. As a 'minimally viable' description it earns a 3, but there is ample room to add usage or workflow context without risking bloat.
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 7-parameter create operation with no output schema, this description is thin. It does not explain what happens after creation, how the response should be used, or how this tool fits into the broader trip workflow among 34 siblings. An agent has no context that creating a trip is likely the first step before adding items, activities, or collaborators.
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 100%, so the schema fully documents all 7 parameters including formats (YYYY-MM-DD), defaults (USD, UTC), and examples. Per the rubric baseline, a 3 is appropriate when the schema carries the parameter documentation burden. The description itself contributes no parameter information, but none is needed given complete 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 uses a specific verb and resource ('Create a new trip') that clearly states the operation, matching the tool name and annotation title. It is distinguishable from nearby siblings like trip_update (modify existing), trip_get (read), and trip_item_add (add to a trip). However, it does not explicitly differentiate itself from trip_clone, which also produces a new trip.
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 gives zero guidance on when to use this tool versus alternatives. An agent cannot tell whether creating a trip is a required prerequisite for trip_item_add or trip_task_create, nor when trip_clone would be the better choice for generating a trip. No context, prerequisites, or exclusions are provided.
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.
Most tools are clearly separated by resource type and action, making selection. The main ambiguity is between trip_item_add and trip_transport_add, since trip_item_add lists transport as a category but trip_transport_add explicitly says to always use it instead for transport.
The naming pattern is highly consistent: trip_<resource>_<action>. Minor deviations exist with bare verbs like search and fetch, and trip_review uses a verb-only style, but these are easy to understand within the larger pattern.
37 tools is a large surface that exceeds the typical coherence threshold. While the domain is broad, the count makes the server feel heavy and harder for an agent to navigate compared to a more focused toolset.
The toolset provides strong CRUD/lifecycle coverage across trips, items, notes, tasks, locations, collaborators, shares, and transport, plus review and search capabilities. Minor gaps exist, such as no direct collaborator add, no location update, and no item-level comment delete, but these are workable.