mcp-route-master

Booking steps for a chosen bus

booking_steps

Read-onlyIdempotent

Guides users through booking a chosen bus on the official site with ordered steps and stop points for seats, boarding, details, confirmation, and payment.

Instructions

Step-by-step script to book the chosen bus on the official site in the user's own browser.

Use when the user wants to book a bus from rank_buses. A script for the assistant (don't paste it to the user): the details to collect and every click in order, with STOP points where the user decides (seats, boarding point, permission to enter details, "confirm" on the summary, and payment).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "origin": "<origin>",
      "destination": "<destination>",
      "travel_date": "<travel_date>",
      "operator": "<operator>",
      "departure": "<departure>"
    },
    "name": "booking_steps"
  }
}

Input Schema

Name	Required	Description
`site`	No	Booking site to use (default redBus).
`seats`	No	Seat numbers the user wants, if already chosen.
`origin`	Yes	From city.
`operator`	Yes	Operator of the chosen bus, as shown.
`departure`	Yes	Departure time of the chosen bus, HH:MM.
`destination`	Yes	To city.
`travel_date`	Yes	Travel date, YYYY-MM-DD (IST).
`for_traveller`	No	True when you can't control the user's browser (e.g. ChatGPT, Gemini): returns short steps for the user to follow themselves instead of a script for you.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.7.0Nov 5, 2026

TDQS

A3.9/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint/idempotent/non-destructive, so the bar is lower, but the description adds real context: this tool produces a script rather than performing the booking, it must not be pasted to the user, and it contains explicit STOP points (seats, boarding point, permissions, summary confirm, payment) where the human decides. It does not state what happens on failure or when the bus is unavailable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in sentence one, and sentence two efficiently packs the trigger condition, the audience warning, and the STOP-point map. The parenthetical numbering of STOP reasons is dense but each item earns its place; nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter, 5-required tool with no output schema, the description does describe the shape of the output (ordered clicks plus STOP points) and the safety framing is carried by annotations. Gaps remain around fallbacks when a seat or site is unavailable, which matters for a booking flow.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all eight parameters are already documented, and the description's 'details to collect' only gestures at them without adding format or constraint detail. The one nuance it conveys indirectly ('don't paste it to the user') maps to for_traveller but doesn't explain that switch explicitly, so 3 is the honest baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence names a specific artifact and resource: a 'step-by-step script to book the chosen bus' in 'the user's own browser', which is far more precise than a generic 'book bus'. It also anchors the input to rank_buses, but never distinguishes itself from booking_summary or page_action, so the sibling boundary is only implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Use when the user wants to book a bus from rank_buses' gives a clear triggering condition tied to a named sibling, and the STOP-point list sketches the flow the agent is entering. It stops short of stating when NOT to use it (e.g. before the user has chosen a bus, or when booking_summary is the better call).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server