bart_tripPlan a trip between two BART stations. Returns schedule, fares, and transfer info.
| Name | Required | Description | Default |
|---|---|---|---|
| date | No | Date MM/DD/YYYY | |
| time | No | Departure time e.g. '5:30pm' | |
| origin | Yes | Origin station code | |
| destination | Yes | Destination station code |
| Name | Required | Description | Default |
|---|---|---|---|
| trips | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Output schema / (root)Previous value: -nullNew value: +{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "additionalProperties": false,
+ "properties": {
+ "trips": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "destination": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "destinationTime": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "durationMinutes": {
+ "type": [
+ "number",
+ "null"
+ ]
+ },
+ "fare": {
+ "type": [
+ "number",
+ "null"
+ ]
+ },
+ "legs": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "destination": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "line": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "origin": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "trainHeadStation": {
+ "type": [
+ "string",
+ "null"
+ ]
+ }
+ },
+ "required": [
+ "origin",
+ "destination",
+ "line",
+ "trainHeadStation"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "option": {
+ "type": "number"
+ },
+ "origin": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "originTime": {
+ "type": [
+ "string",
+ "null"
+ ]
+ }
+ },
+ "required": [
+ "option",
+ "origin",
+ "destination",
+ "originTime",
+ "destinationTime",
+ "durationMinutes",
+ "fare",
+ "legs"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "trips"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds that it returns schedule, fares, and transfer info, but does not disclose other behavioral traits such as data freshness, timezone handling, or multiplicity of results. It does not contradict 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?
The description is two sentences: the first states the core purpose, the second summarizes the return value. It is front-loaded and every word earns its place with no redundancy or ambiguity.
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?
Given the output schema exists and annotations provide safety context, the description is adequate for a tool of moderate complexity. It covers the essential purpose and outputs, though it could note prerequisites (e.g., valid station codes) or clarify that it returns full trip plans with transfers. However, these are not critical gaps.
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 already documents all parameters (origin, destination, date, time) with reasonable descriptions. The tool description adds no additional parameter semantics beyond reiterating that it is between two stations, which is already implied by the schema fields. Baseline of 3 applies.
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 ('Plan') and resource ('trip between two BART stations') and clearly states what it returns ('schedule, fares, and transfer info'). It is clear but does not explicitly differentiate from sibling tools like bart_departures or bart_fare, though the combined output implies a distinct purpose.
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 implies usage when planning a trip between two stations and lists the outputs, but it does not explicitly state when to choose this tool over alternatives (e.g., bart_departures for departures only, bart_fare for fares only). No exclusions or alternatives are mentioned.
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 have clearly distinct purposes, but bart_advisories and bart_status_summary both relate to service status, and bart_trip includes fare information alongside bart_fare. Descriptions help clarify the intended use of each, so the overlap is minor.
All tools consistently use the 'bart_' prefix followed by a descriptive noun phrase in snake_case (e.g., bart_stations, bart_fare, bart_trip). This creates a predictable and uniform naming pattern.
Seven tools is well-scoped for a transit information server, covering station lookup, departures, advisories, fares, and trip planning without unnecessary redundancy or bloat.
The tool set comprehensively covers the core BART transit needs: station discovery, real-time departures, trip planning, fare calculation, and service advisories. No obvious gaps exist for typical transit-related queries.