NOAA Climate Data

get_climate_data

Get climate observations from NOAA Climate Data Online.

Returns historical weather measurements such as temperature, precipitation,
and snowfall. You must provide either a station_id or a FIPS code to
identify the location, and a date range.

Args:
    station_id: NOAA station identifier (e.g. 'GHCND:USW00094728' for Central Park).
    fips: FIPS code for county or state (e.g. '36' for New York state, '36061' for Manhattan).
    dataset: Dataset ID. Common values: 'GHCND' (daily summaries), 'GSOM' (monthly),
             'GSOY' (annual), 'NORMAL_DLY' (daily normals). Default is 'GHCND'.
    start_date: Start date in YYYY-MM-DD format. Required for most datasets.
    end_date: End date in YYYY-MM-DD format. Required for most datasets.
    data_types: Comma-separated data type IDs to filter. Common types:
                TMAX (max temp), TMIN (min temp), TAVG (avg temp),
                PRCP (precipitation), SNOW (snowfall), SNWD (snow depth),
                AWND (avg wind speed). If omitted, all available types are returned.
    limit: Maximum number of records to return (default 100, max 1000).

Input Schema

TableJSON Schema

Name	Required	Default
`fips`	No
`limit`	No
`dataset`	No	GHCND
`end_date`	No
`data_types`	No
`start_date`	No
`station_id`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

TDQS

A4.2/5.0

Behavior4/5

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

No annotations are provided, so the description carries the transparency burden. It discloses key behaviors: returns historical weather measurements, default limit of 100 and max 1000, and that omitting data_types returns all available types. It does not discuss error handling or rate limits, but the existence of an output schema reduces the need to explain return structure.

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?

The description is well-structured with a short overview followed by an Args list. It is appropriately sized for seven parameters and avoids unnecessary fluff. Minor repetition exists (e.g., defaults are stated both in prose and in the Args list), but this does not harm clarity.

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 seven-parameter tool with zero schema descriptions and no annotations, the description covers all parameters, provides examples, and clarifies optional defaults. The output schema exists, so the lack of return-value explanation is acceptable. It could be slightly more complete by noting dataset-specific prerequisites or explicit sibling tool guidance, but overall it is highly usable.

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

Parameters5/5

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

The input schema provides no descriptions (0% schema description coverage), yet the description fully compensates by explaining every parameter with concrete examples: station_id ('GHCND:USW00094728' for Central Park), FIPS ('36' for New York, '36061' for Manhattan), dataset values, date format, data_types with common IDs, and limit defaults. This gives the agent far more than the schema alone.

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?

The description clearly states the action ('Get climate observations from NOAA Climate Data Online') and the resource ('NOAA Climate Data Online'), with concrete examples of returned data ('temperature, precipitation, and snowfall'). This distinguishes it from sibling tools like find_stations (station lookup) and get_climate_normals (normals, not historical observations).

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 description states the mandatory inputs ('You must provide either a station_id or a FIPS code ... and a date range'), which is a key usage requirement. However, it does not explicitly mention when to use this tool instead of the sibling tools, nor does it reference alternatives for station lookup (find_stations) or normals (get_climate_normals).

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

All NOAA Climate Data tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation5/5

Each tool has a distinct role: station discovery, historical data retrieval, and normals retrieval. The descriptions clearly differentiate the two data retrieval tools by their outputs and parameters. No overlap would cause misselection.

Naming Consistency5/5

All three tools follow a consistent verb_noun pattern with snake_case. The verbs find and get are both appropriate for retrieval actions and follow a clear convention.

Tool Count5/5

With only 3 tools, the server is tightly focused on its purpose. Each tool is necessary and the count is within the natural range for a small domain-specific server.

Completeness4/5

The core workflow of finding stations and retrieving climate data or normals is covered. Minor gaps include no tool for listing available datasets or data types, but the provided examples make the surface workable.

Resources

Need Help?