Skip to main content
Glama

Historical weather measurements

get_weather_history
Read-only

Retrieve historical weather measurements from an official SwissMetNet station over a specified date range to analyze past conditions and trends.

Instructions

Historical measurements from an official SwissMetNet station over a date range (recent weeks), delivered via the api.existenz.ch proxy. Station codes are 3-letter MeteoSwiss codes, e.g. 'SMA' Zürich-Fluntern, 'BER' Bern, 'GVE' Geneva; see get_current_measurements station IDs. Long ranges are downsampled: precipitation and sunshine are summed per bucket (totals preserved), other parameters averaged with min/max.

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": {
      "station_code": "<station_code>",
      "date_from": "<date_from>"
    },
    "name": "get_weather_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
date_toNoEnd date (default: today)
date_fromYesStart date YYYY-MM-DD
parameterNotemperature
station_codeYesSwissMetNet station code, e.g. 'SMA'

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.3

TDQS

A4.5/5.0
Behavior5/5

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

Beyond readOnlyHint and openWorldHint, the description discloses the upstream data source and proxy (api.existenz.ch), the data-availability window (recent weeks), and exact downsampling semantics: precipitation and sunshine summed per bucket with totals preserved, other parameters averaged with min/max. That aggregation behavior materially changes how an agent must interpret results.

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?

Two dense sentences, front-loaded with what the tool returns before details on codes and downsampling. The three station examples are slightly redundant but cheap and genuinely clarifying.

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 4-parameter read-only tool with no output schema, the definition covers station identification, date range bounds, data window, and aggregation semantics. The one gap is that the per-measurement return shape (fields, bucket granularity) is only implied by the downsampling note.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 75% schema coverage, the schema already documents station_code and dates, but the description adds the 3-letter MeteoSwiss code convention with three concrete examples and the pointer to get_current_measurements for station IDs. It also implies how the 'parameter' selection affects aggregation, though it does not enumerate the enum values.

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 (retrieves historical measurements), a specific resource (official SwissMetNet station data), and scope (date range, recent weeks), and implicitly separates itself from get_current_measurements by pointing there for station IDs. An agent can distinguish this from the current-conditions and generic get_weather siblings.

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?

Establishes when this tool applies (past data over a date range, limited to recent weeks) and routes the agent to get_current_measurements for station ID lookup. It stops short of explicitly stating when NOT to use it versus get_weather or get_water_history, but the historical/current split is clear.

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