uber_tripsRetrieve upcoming and past rides with destination, time, fare, and Uber page links; use a cursor to page through trip history.
Upcoming (on the first page) and past trips: id, where to, when, fare, Uber's page for it. Page back with next_cursor.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | How many past trips, newest first | |
| cursor | No | next_cursor from the previous call |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.3.15Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, and the description still adds non-obvious behavior: upcoming trips appear only on the FIRST page, and older trips require cursor paging. That ordering quirk is exactly the kind of thing an agent would otherwise get wrong.
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?
Two tight sentences with no filler; the important scope fact (upcoming on the first page) is front-loaded ahead of the pagination instruction.
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?
With an output schema present, return values need not be explained, and pagination plus the upcoming/past split are covered. What's left out is authorization context (openWorldHint implies a linked Uber account) and an explicit pointer to uber_trip for a single trip.
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 coverage is 100%, so both parameters are already documented, and the schema itself states cursor comes from the prior call's next_cursor. The description's 'page back with next_cursor' largely restates that; it adds only the mild clarification that cursor values originate from a response field named next_cursor rather than the parameter name.
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 names the resource (upcoming and past trips) and enumerates the returned fields (id, destination, time, fare, Uber page link), so an agent knows exactly what this returns. It does not explicitly contrast with the singular sibling uber_trip, so the plural/singular split must be inferred from the name alone.
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?
Usage is implied rather than stated: the agent can infer this is the history-listing tool, and it gets concrete guidance for pagination ('page back with next_cursor'). But there is no explicit when-to-use versus uber_trip or uber_ride_status, and no exclusion of e.g. active-ride checks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.