BinaSmart

Cancel a ride

cancel_ride

DestructiveIdempotent

Cancels a BinaSmart ride that has not started yet. A cancellation cannot be undone. Needs the ride id and the rider phone used to book.

Input Schema

Name	Required	Description	Default
`ride_id`	Yes	Ride id returned by request_ride
`rider_phone`	Yes	Ethiopian phone number used to book the ride, in the form 09xxxxxxxx or +2519xxxxxxxx

Output Schema

Name	Required	Description
`note`	No	How to use or present this result
`test`	No	true for a reviewer test booking (no driver is sent)
`tier`	No	Vehicle tier
`driver`	No	Assigned driver, null until one is assigned
`pickup`	No	Pickup place
`status`	No	dispatching, assigned, arriving, arrived, ontrip, completed, cancelled, or test_booking
`dropoff`	No	Drop-off place
`ride_id`	No	Ride id (needed for get_ride_status and cancel_ride)
`fare_etb`	No	Fixed fare in birr
`source_url`	No	bina.et page this result comes from; cite it
`requested_at`	No	When the ride was requested (ISO time)
`tracking_url`	No	Live tracking page
`payment_method`	No	cash, telebirr or chapa
`payment_status`	No	Payment status

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 18, 2026

changedInput schema / properties / rider_phone / description

Previous value: -"Ethiopian phone number used to book the ride, e.g. 0911234567 or +251911234567"New value: +"Ethiopian phone number used to book the ride, in the form 09xxxxxxxx or +2519xxxxxxxx"

Changed3 schema fields changedOct 18, 2026

addedInput schema / properties / ride_id / description
```
Added value: +"Ride id returned by request_ride"
```

addedInput schema / properties / rider_phone / description

Added value: +"Ethiopian phone number used to book the ride, e.g. 0911234567 or +251911234567"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "driver": {
+      "anyOf": [
+        {
+          "additionalProperties": true,
+          "properties": {
+            "name": {
+              "description": "Driver name",
+              "type": [
+                "string",
+                "null"
+              ]
+            },
+            "phone": {
+              "description": "Driver phone",
+              "type": [
+                "string",
+                "null"
+              ]
+            },
+            "plate": {
+              "description": "Plate number",
+              "type": [
+                "string",
+                "null"
+              ]
+            },
+            "rating": {
+              "anyOf": [
+                {
+                  "type": [
+                    "number",
+                    "string"
+                  ]
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Driver rating"
+            },
+            "vehicle": {
+              "description": "Vehicle"
+            }
+          },
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Assigned driver, null until one is assigned"
+    },
+    "dropoff": {
+      "description": "Drop-off place",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "fare_etb": {
+      "anyOf": [
+        {
+          "type": [
+            "number",
+            "string"
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Fixed fare in birr"
+    },
+    "note": {
+      "description": "How to use or present this result",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "payment_method": {
+      "description": "cash, telebirr or chapa",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "payment_status": {
+      "description": "Payment status",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "pickup": {
+      "description": "Pickup place",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "requested_at": {
+      "description": "When the ride was requested (ISO time)",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "ride_id": {
+      "description": "Ride id (needed for get_ride_status and cancel_ride)",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "source_url": {
+      "description": "bina.et page this result comes from; cite it",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "status": {
+      "description": "dispatching, assigned, arriving, arrived, ontrip, completed, cancelled, or test_booking",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "test": {
+      "description": "true for a reviewer test booking (no driver is sent)",
+      "type": [
+        "boolean",
+        "null"
+      ]
+    },
+    "tier": {
+      "description": "Vehicle tier",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "tracking_url": {
+      "description": "Live tracking page",
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "type": "object"
+}

First observedSep 6, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true, so the irreversibility is partially covered; the description reinforces it with 'A cancellation cannot be undone' and adds the booking-phone requirement as an identity check. It does not discuss idempotency or failure behavior, but the safety profile is conveyed.

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?

Three short sentences, front-loaded with the action and its precondition, then irreversibility, then prerequisites. No filler.

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 two-parameter destructive tool with an output schema and annotations covering the safety profile, the description supplies everything an agent needs: what it does, the precondition, irreversibility, and required inputs.

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%, with both ride_id and rider_phone fully documented including phone formats. The description only restates that the ride id and booking phone are needed, adding no new syntax beyond the schema, so the baseline 3 applies.

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 (cancels) and resource (BinaSmart ride) plus a scoping precondition (has not started yet). This distinguishes it from quote_ride, request_ride, and get_ride_status without needing the schema.

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?

Clearly states the applicable condition ('has not started yet') and the prerequisites (ride id and the rider phone used to book). It does not explicitly name alternative tools, so it stops short of a 5.

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

All BinaSmart 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.