Skip to main content
Glama

Surroundings of a home

get_home_environment
Read-onlyIdempotent

Greenery and emission sources around a point (a home): tree canopy share within 300 m, green land share and summer NDVI within 500 m with a low/medium/high level against the rest of the city, the nearest park, up to 10 emission sources (power plants, works and mines within 5 km, landfills within 3 km, boiler houses and single chimneys within 1.5 km) chosen by significance (high/medium/low, from emissions, fuel and size) and distance, with distance, bearing, fuel, confidence, significance, wind_exposure (the share of the time the wind blows from the source to the home, from the wind rose of the region) and, for facilities in the Climate TRACE registry, yearly CO2e, and the number of detached houses within 1 km (an estimate of stove smoke, not a count of stoves). Only computed cities; elsewhere the error city_not_covered.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "lat": "<lat>",
      "lon": "<lon>"
    },
    "name": "get_home_environment"
  }
}

Input Schema

NameRequiredDescriptionDefault
latYes
lonYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive behavior, yet the description adds substantial extra context: per-category search radii, the cap of 10 sources with significance and distance ranking, wind_exposure derived from the regional wind rose, Climate TRACE CO2e enrichment, and the explicit city_not_covered failure mode. The estimate caveat 'an estimate of stove smoke, not a count of stoves' is exactly the kind of nuance that prevents misinterpretation. It only lacks the response shape or ordering of returned sources.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Every clause carries real information about the returned payload, so little is filler, but it is delivered as a single run-on sentence of roughly 120 words with nested parentheses, which makes it hard to scan. Key routing facts (coverage constraint, error name) are buried at the end rather than front-loaded.

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?

With no output schema available, the description must carry the return-value burden and largely does, enumerating each returned field (canopy share, green land share, NDVI level, nearest park, source attributes, house count). What remains unstated is whether fields can be null when a category is unavailable, which matters for an open-ended enrichment response.

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 0%, so the schema documents only name, type and bounds for lat/lon. The description clarifies the conceptual meaning of the point ('a home') but adds no format, CRS or precision guidance beyond what the schema's -90/90 and -180/180 bounds already convey. With two self-evident parameters this is adequate but not additive.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a precise resource: greenery and emission sources around a home, with explicit radii (300 m canopy, 500 m NDVI, 5/3/1.5 km source bands) and ranking logic. It is clearly distinct from siblings like get_air_quality or get_sensor. It stops short of a crisp verb-first statement of purpose, opening instead with a noun phrase.

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?

Usage is only implied: supply lat/lon for a home's surroundings. The one real guideline is a coverage constraint, 'Only computed cities; elsewhere the error city_not_covered'. No alternative tool is named for cases like air quality at a point, so the agent must infer when to prefer get_air_quality or get_city_forecast.

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