BinaSmart MCP Server

Search BinaSmart knowledge

search_knowledge

Read-only

Search BinaSmart's knowledge base for answers on services, Ethiopian paperwork, and getting around Addis Ababa. Returns best-matching passages with source URLs; use quote_ride for exact fares.

Instructions

Semantic search over BinaSmart's knowledge base: every service (BinaRide, BinaPool shared commute, Bina Airport, hotels, cinema, BinaWatch, insurance, flights, property, cars, tenders), the product rules (fixed fares, what is demo, payments), the 25 Digital Ethiopia guides, and practical Addis Ababa knowledge (neighbourhoods, transport hubs, Ethiopian time and calendar, emergency numbers). For questions about BinaSmart, Ethiopian paperwork or getting around Addis. Returns the best-matching passages, each with its source url. Exact fares are not in the passages: they come from quote_ride.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`k`	No	How many passages (default 4)
`query`	Yes	Question or keywords, English or Amharic

Output Schema

TableJSON Schema

Name	Required	Description
`note`	No	How to use or present this result
`query`	No	The query searched
`results`	No	Best-matching passages

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.1.2Oct 18, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "note": {
+      "description": "How to use or present this result",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "query": {
+      "description": "The query searched",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "results": {
+      "anyOf": [
+        {
+          "items": {
+            "additionalProperties": true,
+            "properties": {
+              "score": {
+                "description": "Relevance",
+                "type": [
+                  "number",
+                  "null"
+                ]
+              },
+              "source_url": {
+                "description": "Page it comes from",
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "text": {
+                "description": "Passage",
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "title": {
+                "description": "Passage title",
+                "type": [
+                  "string",
+                  "null"
+                ]
+              }
+            },
+            "type": "object"
+          },
+          "type": "array"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Best-matching passages"
+    }
+  },
+  "type": "object"
+}

First observedv0.1.0Oct 18, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered and the description adds the boundary of the corpus plus the result shape ('best-matching passages, each with its source url'). It stops short of noting result-count behaviour beyond k or any ranking/coverage caveats, but adds real context beyond the annotations.

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?

Three sentences, front-loaded with the verb+resource before the coverage list. The long parenthetical enumeration of services is dense but it is the information that makes scope unambiguous; nothing is padding, though it could be trimmed slightly.

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?

An output schema and annotations exist, so the description does not need to explain return values; it still summarises them briefly. Purpose, corpus scope, use conditions, and the fare exception are all present, leaving nothing an agent needs before calling it.

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 both parameters carry their own descriptions including the default of k and the English/Amharic input allowance. The description adds no further parameter guidance, 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 and resource ('Semantic search over BinaSmart's knowledge base') and then enumerates the corpora it covers, so an agent can tell exactly what content is reachable. It also distinguishes itself from quote_ride on the one point of overlap (exact fares).

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 use condition ('For questions about BinaSmart, Ethiopian paperwork or getting around Addis') and an explicit exclusion with the alternative to use instead ('Exact fares are not in the passages: they come from quote_ride'). The agent is routed rather than left to guess.

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