Skip to main content
Glama

Airsockfly

Cancel booking

cancel_booking
DestructiveIdempotent

Cancel a booking. This is irreversible: call preview_cancellation, tell the user the penalty and refund, and set confirm to true only after the user explicitly agreed.

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": {
      "vertical": "<vertical>",
      "bookingId": "<bookingId>",
      "confirm": "<confirm>"
    },
    "name": "cancel_booking"
  }
}

Input Schema

NameRequiredDescriptionDefault
reasonNoShort reason given by the user.
confirmYesMust be true. Set it only after the user explicitly confirmed this action.
verticalYesService type.
bookingIdYesIdentifier of one booking inside an order, from get_booking.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is partly structured. The description adds the key behavioral fact annotations cannot express: the call is irreversible and requires human confirmation before execution, which is what an agent most needs to know about a destructive commit. It stops short of describing post-cancellation effects (refund timing, whether the booking row persists).

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

Conciseness5/5

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

Two sentences, no waste, with the irreversible nature front-loaded before the procedural instructions. Every clause carries operational weight.

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?

Complete for a destructive single-record mutation: irreversibility, sequencing, and the confirmation gate are all present, and no output schema exists to require return-value explanation. Minor gap in not stating what the caller receives after the cancellation succeeds or how refunds are represented.

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 coverage is 100%, including per-parameter descriptions for confirm, bookingId provenance, and the vertical enum, so the schema carries the semantic load. The description reinforces the confirm gating rule but adds no syntax or format detail beyond it. Baseline 3 is appropriate.

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

Purpose5/5

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

States a specific verb and resource ("Cancel a booking") and immediately distinguishes itself from the sibling preview_cancellation by naming it as the required prior step. An agent can tell the committing action apart from the read-only preview without opening either schema.

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

Usage Guidelines5/5

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

Gives an explicit ordered workflow: call preview_cancellation, relay penalty and refund to the user, then set confirm to true only after explicit user agreement. It names both the alternative and the precondition that selects it, leaving nothing to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources