Skip to main content
Glama

noaa-climate-mcp-server

Search NOAA Storm Events

noaa_climate_search_storm_events
Read-only

Search the NCEI Storm Events Database for one calendar year — tornadoes, hail, floods, hurricanes, winter storms, heat, and every other NWS Storm Data event type, with magnitude, direct and indirect deaths and injuries, property and crop damage, and the episode and event narratives. This is a different NOAA corpus from the CDO tools on this server: it carries discrete severe-weather events rather than station observations, needs no token, and is published as one bulk file per year, so year is required. Filter with state (the full upper-case name NCEI writes, e.g. "FLORIDA" — not the postal code "FL"), eventType (the exact NWS label, e.g. "Tornado", "Hail", "Flash Flood", "Hurricane (Typhoon)", matched case-insensitively), month, and minDamageInUsd. Damage arrives from NCEI as a magnitude-suffixed string ("75.00K", "1.20M", "1.00B") and is returned as both the raw cell and a parsed dollar amount; an unreported figure is omitted entirely rather than reported as zero, and minDamageInUsd therefore excludes those rows and says how many it dropped. Results come back in the source file's own row order, paged with limit and offset, and totalCount is the true match count for the whole year.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
yearYesCalendar year to search (1950 through the current partial year). Required — NCEI publishes one file per year, so an unscoped search would download every year back to 1950.
limitNoMaximum number of events to return (1–100). Defaults to 50.
monthNoFilter to events whose begin date falls in this month (1–12). Optional.
stateNoFilter to this state or territory, written as the full name NCEI uses (e.g. "FLORIDA", "PUERTO RICO"), matched case-insensitively. Postal codes like "FL" match nothing. Optional.
offsetNoZero-based index of the first matching event to return. Defaults to 0.
eventTypeNoFilter to this NWS event type, matched case-insensitively against the exact label (e.g. "Tornado", "Hail", "Flash Flood", "Hurricane (Typhoon)"). A miss returns the labels present in that year. Optional.
minDamageInUsdNoFilter to events whose property damage parses to at least this many dollars. Excludes every row whose damage NCEI did not report — about a fifth of a recent year — since an unreported figure cannot be shown to clear the threshold. Optional.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
capNoThe limit that was applied. Omitted otherwise.
yearNoThe calendar year searched.
errorNoPresent when the call failed. Absent on success.
shownNoEvents returned on this page. Omitted otherwise.
eventsNoMatching events for the requested page, in the source file’s own row order.
noticeNoGuidance when nothing matched or the page ran past the end. Omitted otherwise.
exhaustedNoTrue when offset is past the end of a non-empty match set — the page is empty but matches exist. Omitted otherwise.
truncatedNoTrue when more matches exist beyond this page. Omitted otherwise.
sourceFileNoThe exact NCEI file this page was read from, including its `_c<publishDate>` suffix — the suffix changes whenever NCEI republishes a year.
totalCountNoEvents matching every filter across the whole year, before offset and limit.
scannedRowCountNoRows read from the source file, matched or not. Omitted when unavailable.
excludedUnknownDamageNoRows that satisfied every other filter but were dropped by minDamageInUsd because NCEI reported no property-damage figure for them. Omitted when minDamageInUsd was not supplied.

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only provide readOnlyHint and openWorldHint, so the description carries the transparency burden. It discloses non-obvious behaviors: damage arrives as magnitude-suffixed strings and is parsed, unreported damage is omitted rather than zeroed, minDamageInUsd excludes unreported rows and reports how many were dropped, results come in source row order, and totalCount is the true match count for the full year. This far exceeds what annotations convey and contains no contradiction.

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?

Although long, every sentence earns its place: the main purpose is front-loaded, then the contrast with CDO tools, then filter specifics with examples, then the critical damage-parsing and pagination/totalCount behaviors. Dense but efficiently organized with no filler.

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?

For a tool with 7 parameters, 1 required, and an output schema, the description covers everything an agent needs to call it correctly: the required year, filter semantics with examples, the tricky damage exclusion behavior, ordering, pagination, and the meaning of totalCount. Nothing important is missing, and the output schema handles return details.

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?

Schema coverage is 100%, so baseline is 3. The description adds meaningful semantics beyond the schema for minDamageInUsd (omission behavior, exclusion logic, reported drop count) and clarifies the damage string format. However, for state and eventType it largely repeats schema examples, so it doesn't fully earn a 5.

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 ('Search'), a specific resource ('NCEI Storm Events Database'), and a well-scoped subject (one calendar year of events). It enumerates event types and fields returned, and explicitly differentiates from the CDO tools on the server, making it easy for an agent to distinguish this from siblings.

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?

Explicitly contrasts with CDO tools ('different NOAA corpus... discrete severe-weather events rather than station observations'), states that no token is needed, and explains why year is required ('published as one bulk file per year'). This gives an agent clear when-to-use and when-not guidance, including the condition that drives the required parameter.

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.

TDQS

A4.6/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: fetching data, searching locations, searching stations, getting station metadata, listing categories/datasets/types, and listing location categories. No two tools overlap; an agent can easily select the correct one based on the task.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern in snake_case: fetch_data, find_locations, find_stations, get_station, list_data_categories, list_datasets, list_data_types, list_location_categories. The verbs (fetch, find, get, list) are semantically appropriate and predictable.

Tool Count5/5

With 8 tools, the server is well-scoped for a climate data API. It covers the essential discovery and retrieval workflow without unnecessary bloat. Each tool serves a clear role in fetching or finding climate data elements.

Completeness5/5

The tool set provides a complete workflow: discover datasets, data categories, data types, location categories, find locations, find stations, get station metadata, and fetch observation data. There are no obvious gaps for the stated purpose of accessing NOAA climate data.