Skip to main content
Glama

Horseback: zajęcia na Jurze

Jak do nas trafić

get_directions
Read-onlyIdempotent

Use this when the user asks where Horseback is or how to get there (gdzie to jest, jak dojechać, dojazd do Huciska): returns the address, GPS coordinates, Google Maps links (place and route), opening hours of classes and transport for groups. It has no data on public transport or parking - for these, give the user the contact details it returns. Use it also when a group (school, company) asks only how to get there or about a coach - do not call get_group_trip_offer for such questions.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_directions"
  }
}

Input Schema

NameRequiredDescriptionDefault
languageNoLanguage of the returned texts: "pl" (Polish, default) or "en" (English). Use the language of the conversation.

Output Schema

NameRequiredDescriptionDefault
hoursNoPhone support and class hours.
contactNoHorseback contact: phone, email, website, social profiles.
languageYesLanguage of the returned texts.
locationNoName and address of the centre.
googleMapsYes
notCoveredNo
coordinatesNo
descriptionNo
directionsPageNo
groupTransportNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "contact": {
      +      "description": "Horseback contact: phone, email, website, social profiles.",
      +      "type": "object"
      +    },
      +    "coordinates": {
      +      "properties": {
      +        "latitude": {
      +          "type": "number"
      +        },
      +        "longitude": {
      +          "type": "number"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "description": {
      +      "type": "string"
      +    },
      +    "directionsPage": {
      +      "type": "string"
      +    },
      +    "googleMaps": {
      +      "properties": {
      +        "place": {
      +          "type": "string"
      +        },
      +        "route": {
      +          "type": "string"
      +        }
      +      },
      +      "required": [
      +        "place",
      +        "route"
      +      ],
      +      "type": "object"
      +    },
      +    "groupTransport": {
      +      "properties": {
      +        "heading": {
      +          "type": "string"
      +        },
      +        "text": {
      +          "type": "string"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "hours": {
      +      "description": "Phone support and class hours.",
      +      "type": "object"
      +    },
      +    "language": {
      +      "description": "Language of the returned texts.",
      +      "enum": [
      +        "pl",
      +        "en"
      +      ],
      +      "type": "string"
      +    },
      +    "location": {
      +      "description": "Name and address of the centre.",
      +      "type": "object"
      +    },
      +    "notCovered": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "language",
      +    "googleMaps"
      +  ],
      +  "type": "object"
      +}
  2. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, closed-world behavior, so the safety profile is covered. The description adds genuine non-annotation context: the exact content scope, the explicit gap (no public transport or parking data) and the fallback action for that gap. It stops short of describing pagination or response shape, but an output schema exists and the content list is partly redundant with it.

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?

Front-loaded with the trigger condition before the payload, then the data gaps, then the sibling-routing caveat. Every clause earns its place: no filler, and the negative routing rule is placed last where it is easiest to act on.

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?

With annotations, a 100%-documented single parameter, and an output schema already covering return values, the description closes the remaining gaps an agent needs: when to call it, what topics it cannot answer, and which sibling to avoid.

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?

Only one optional enum parameter (language) with 100% schema coverage, so the schema already explains default 'pl' and the conversation-language rule. The description adds no meaning beyond it, which is the expected baseline when the schema does the work.

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+resource (get directions) and enumerates exactly what it returns: address, GPS coordinates, Google Maps place/route links, class opening hours, and group transport. It also explicitly distinguishes itself from get_group_trip_offer, so an agent can route 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 concrete trigger phrases in two languages (gdzie to jest, jak dojechać, dojazd do Huciska) plus an explicit negative rule: for group/coach questions call this instead of get_group_trip_offer. It also tells the agent what to do when data is missing (hand over the returned contact details rather than guessing).

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