Transit trip plans and live departures for Massachusetts: MBTA, regional buses, Amtrak, ferries.
Scored across 2 tools
next_departures is clearly a station departure-board query, while plan_trip is an end-to-end itinerary planner. Their user intents are distinct, and the descriptions make the boundary clear even though both can return live timing information.
Both names use clear snake_case, but next_departures is a noun phrase while plan_trip follows a verb_noun pattern. The inconsistency is minor and still readable.
Two tools cover the two main transit intents, but the surface feels thin for a transit server. Users may reasonably expect additional operations such as station search, route lookup, or service alerts.
The core workflows of checking departures and planning trips are covered, but notable gaps remain around station/route lookup and service alerts or disruption status. Agents can work around some gaps through plain-language plan_trip queries, but not all of them.
Live departures at one MBTA station (subway, Commuter Rail, bus, ferry), optionally for one route or line.
| Name | Required | Description | Default |
|---|---|---|---|
| stop | Yes | MBTA station name, e.g. 'North Station', 'Park Street', 'Harvard'. | |
| limit | No | How many departures (default 8). | |
| route | No | Optional line or route, e.g. 'Red Line', 'Green Line D', '39', 'Rockport'. |
| Name | Required | Description |
|---|---|---|
| link | Yes | |
| answer | Yes | |
| departures | No | |
| attribution | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds that results are 'live' (real-time rather than scheduled) and that a single station is queried, but says nothing about data freshness/latency or what happens for an unrecognized station.
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?
A single sentence with no filler, front-loaded with the core action and resource, followed by the mode scope and the optional filter. Nothing is wasted and nothing essential is buried.
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 a fully described 3-parameter schema, complete annotations and an output schema, the definition covers what an agent needs to invoke it. The only shortfall is that real-time data characteristics (refresh behavior, failure mode for ambiguous station names) are left unstated.
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% and an output schema exists, so the schema already documents stop, limit and route with examples and bounds. The description only reinforces that route is optional and single-valued ('one route or line'), adding marginal value beyond the schema.
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?
States a specific resource (live departures) scoped to one MBTA station and enumerates the covered modes (subway, Commuter Rail, bus, ferry), which is more than a restatement of the title. It is clearly a departure-board lookup rather than a journey planner, so an agent can separate it from plan_trip without opening the schema, though the sibling is never named.
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 only implied: 'live departures at one MBTA station' signals real-time schedule lookups versus trip planning. There is no explicit statement of when to prefer this over plan_trip, nor any note about prerequisites such as needing an exact station name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Plan a public transit trip in Massachusetts and nearby Rhode Island and New Hampshire. Ask in plain words, e.g. 'How do I get from South Station to Fenway Park at 6pm?' or 'last train from North Station to Salem tonight'. Returns one clear plan (what to board, when it leaves, where to get off) with live times when available, plus a link that opens it in Cobblehop for live tracking and a stop alert.
| Name | Required | Description | Default |
|---|---|---|---|
| from | No | Optional starting point if the question doesn't name one: a place, address or 'lat,lon'. | |
| lang | No | Answer language (default en). | |
| question | Yes | The trip in the user's words, with the start, destination and time if known. |
| Name | Required | Description |
|---|---|---|
| lang | No | |
| link | Yes | |
| trip | No | |
| answer | Yes | |
| departures | No | |
| attribution | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, non-destructive, open-world, non-idempotent, so safety is covered. The description adds real value beyond that: it returns a single plan (what to board, departure time, where to exit), includes live times when available, and returns a Cobblehop tracking link and stop alert — details absent from the annotations.
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?
Front-loaded with what the tool does and where it works, followed by concrete input examples and expected output. Every sentence contributes; the two example phrasings are slightly redundant but illustrate distinct cases (time-specified trip vs. last-train query).
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?
An output schema exists, so return values need not be spelled out, yet the description still summarizes the plan components and the tracking link. Geographic scope, input style, and output nature are all covered; only the relationship to the sibling next_departures is missing.
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 all three parameters are already documented, establishing a baseline of 3. The description reinforces the question parameter by showing natural-language examples and implies from/lang are optional conveniences, but adds no syntax or format detail beyond the schema.
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?
States a specific verb and resource ('Plan a public transit trip in Massachusetts') and bounds the geography to MA plus nearby RI and NH. The 'one clear plan' framing implicitly separates it from a departures lookup, but the sibling next_departures is never named, so differentiation is left to inference.
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 examples ('How do I get from South Station to Fenway Park at 6pm?', 'last train from North Station to Salem tonight') show the intended input style and hint at trip-planning scenarios. However, there is no explicit when-to-use statement or exclusion relative to next_departures, so the agent must infer the boundary between planning a trip and querying departures.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
next_departuresplan_tripMBTA MCP — Boston real-time transit via the MBTA v3 API (api-v3.mbta.com)
Trips, departures, alerts and vehicles for NYC, DC and the SF Bay Area.
Read-only public transit departures, stop search, and city coverage for bus and train users.
Get real-time NYC bus arrivals, live vehicle locations, and service alerts. Plan trips between any…
Add one secure layer between your agents and this server.