Skip to main content
Glama
Sign In
owntracks-mcp

owntracks-mcp

by de-niji
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

get_last_location

Read-onlyIdempotent

Get the current location of an OwnTracks user or device, or all users, including coordinates, fix age, address, regions, accuracy, speed, battery, and a map link.

Instructions

Current (most recent) position of a user/device, or of everyone if no user is given.

Returns coordinates, time and age of the fix, address (if the Recorder geocodes), regions the device is in, accuracy, speed, battery and a map link. Always mention how old the position is.

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_last_location"
  }
}

Input Schema

NameRequiredDescriptionDefault
userNoOwnTracks user name. "me" = configured default user. Omit for everyone (where supported).
deviceNoDevice name of that user. Omit if the user has only one device.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnly/idempotent/non-open-world, so safety is covered. The description adds a conditional behavior ('address if the Recorder geocodes') and a presentation requirement ('always mention how old the position is'), but the rest of the return list is behavioral filler given an output schema exists.

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?

Front-loaded with the core purpose, then output summary and one actionable instruction. It is short and earns most of its space, though the output enumeration is partially redundant with the output schema.

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?

For a two-param read tool with full schema coverage, annotations, and an output schema, the description supplies everything needed to call it correctly, plus a presentation hint. Only the lack of sibling routing keeps it from being fully complete.

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%, so both parameters are already documented, including the 'me'/omit semantics. The description's 'or of everyone if no user is given' duplicates schema text rather than adding syntax or format detail, so 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+resource ('Current (most recent) position of a user/device') and adds the scope behavior when no user is supplied. The word 'current/most recent' implicitly separates it from get_location_history, so an agent can distinguish it from its siblings.

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

Usage Guidelines3/5

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

The 'or of everyone if no user is given' clause gives a usage condition, but it largely restates the schema default. No sibling tool (get_location_history, owntracks_status, reverse_geocode) is named as an alternative, so the when-to-use routing is only implied.

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

Deploy Server

Other Tools