Andrii Co. Notary & Apostille Assistant

cancel_booking

Destructive

Cancel a booking on the signed-in account — Pending or Scheduled only. Use when the visit is no longer needed; guests cancel via their emailed manage link instead. Accepts: order_id (e.g. copied from my_bookings). Returns a cancellation notice; fails if the booking is not yours, is neither Pending nor Scheduled, or not signed in.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`order_id`	Yes	The booking's order id (from my_bookings).

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	Yes
`status`	No	Account tools: the booking's status after this call (Pending after book_appointment).
`message`	Yes	Customer-facing outcome; relay it as written — bookings are requests until the notary confirms.
`manageUrl`	No	Guest requests: the emailed confirm/cancel link, when one was minted (null otherwise).
`onAccount`	No	True when the request was filed on the signed-in customer's own account — they can then list it with my_bookings and change it with reschedule_booking / cancel_booking. Absent or false means a guest request, managed through the emailed link.
`reference`	No	Request / order reference for check_request_status (guest tools) or my_bookings (account tools).
`appendedToExisting`	No	True when existing_reference was given and the request was extended, not duplicated.
`ourComparableQuoteCents`	No	request_price_match only, when computable.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 6, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "appendedToExisting": {
+      "description": "True when existing_reference was given and the request was extended, not duplicated.",
+      "type": "boolean"
+    },
+    "manageUrl": {
+      "description": "Guest requests: the emailed confirm/cancel link, when one was minted (null otherwise).",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "message": {
+      "description": "Customer-facing outcome; relay it as written — bookings are requests until the notary confirms.",
+      "type": "string"
+    },
+    "ok": {
+      "const": true,
+      "type": "boolean"
+    },
+    "onAccount": {
+      "description": "True when the request was filed on the signed-in customer's own account — they can then list it with my_bookings and change it with reschedule_booking / cancel_booking. Absent or false means a guest request, managed through the emailed link.",
+      "type": "boolean"
+    },
+    "ourComparableQuoteCents": {
+      "description": "request_price_match only, when computable.",
+      "type": "integer"
+    },
+    "reference": {
+      "description": "Request / order reference for check_request_status (guest tools) or my_bookings (account tools).",
+      "type": "string"
+    },
+    "status": {
+      "description": "Account tools: the booking's status after this call (Pending after book_appointment).",
+      "type": "string"
+    }
+  },
+  "required": [
+    "ok",
+    "message"
+  ],
+  "type": "object"
+}

First observedJul 21, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already signal destructive behavior, and the description adds concrete constraints: it only succeeds on Pending/Scheduled bookings, fails when the booking is not yours or the user is not signed in, and returns a cancellation notice. This meaningfully supplements the structured hints without contradicting them.

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 front-load the core action and then cover usage trigger, exclusions, accepted parameter, and failure conditions. Every clause adds decision-relevant information with no filler or redundant explanation.

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

Completeness5/5

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

For a one-parameter destructive tool with an output schema, the description covers purpose, preconditions, failure modes, and result. An agent has enough information to select and invoke this correctly, including knowing not to use it for guests or non-Pending/Scheduled bookings.

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% and the only parameter, order_id, is already described as 'The booking's order id (from my_bookings).' The description repeats this by saying 'e.g. copied from my_bookings,' but does not add new semantic details such as format, length, or validation rules.

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?

Opens with a specific verb and resource: 'Cancel a booking on the signed-in account' and immediately scopes it to 'Pending or Scheduled only.' This clearly identifies the operation and distinguishes it from sibling tools like book_appointment and reschedule_booking.

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?

Explicitly states the trigger: 'Use when the visit is no longer needed,' and provides an exclusion for guests: 'guests cancel via their emailed manage link instead.' It also lists preconditions such as the booking being yours, Pending/Scheduled, and the user being signed in.

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

All Andrii Co. Notary & Apostille Assistant tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?