weather-intel-mcp

Earthquakes

earthquakes

Read-onlyIdempotent

List recent worldwide seismic events from USGS feeds, filtered by magnitude, days, and optional bounding box or point radius. Returns magnitude, place, time, depth, and coordinates.

Instructions

List recent earthquakes worldwide from the USGS feed. Filter by minimum magnitude, look-back window in days, and optionally a bounding box or a point+radius (km). Returns magnitude, place, time, depth and coordinates.

Input Schema

TableJSON Schema

Name	Required	Description
`lat`	No	Optional center latitude for a radius search.
`lon`	No	Optional center longitude for a radius search.
`days`	No	Look back this many days (default 7, max 30).
`limit`	No	Maximum number of quakes to return.
`radius_km`	No	Radius in km around lat/lon (requires lat+lon).
`min_magnitude`	No	Only return quakes at or above this magnitude.

Output Schema

TableJSON Schema

Name	Required	Description
`count`	No
`source`	No
`criteria`	No
`provenance`	No	Where this answer came from. served_at is when Datakoot answered (UTC); upstream lists the official sources consulted. Datakoot may serve a briefly cached copy, so the source's own observation can be older than served_at.
`earthquakes`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv2.1.0Oct 15, 2026

TDQS

A3.6/5.0

Behavior3/5

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

The annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered structurally. The description adds the upstream source (USGS feed), which is useful context, but says nothing about feed freshness/lag, result ordering, or truncation behavior under the limit.

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 compact sentences, front-loaded with what the tool returns and followed by the filter surface. The final clause enumerating returned fields ('magnitude, place, time, depth and coordinates') is wasted since an output schema already exists, but the overall size is appropriate.

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?

Scope, source, filters, and defaults (via schema) are all available, and the output schema removes any need to describe return values. The only substantive omission is operational behavior such as feed lag and ordering, plus the inaccurate bounding-box claim.

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

Parameters2/5

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

Schema coverage is 100%, so the baseline would be 3, but the description claims the agent can filter by 'a bounding box' while the schema exposes only lat/lon/radius_km — there is no bounding-box parameter. This actively misdescribes an invocation option an agent might attempt, offsetting the correct mentions of magnitude, days, and radius.

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 and resource ('List recent earthquakes worldwide') plus the data source ('USGS feed'), which is exactly what an agent needs to recognize this tool. No sibling offers earthquake data, so no disambiguation is required, and the scope is unambiguous.

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 names the available filters (magnitude, days, point+radius), which implies the situations the tool fits, but never states when to prefer it or any exclusions/preconditions. With no competing sibling and all parameters optional, the omitted 'when to use' is low-impact but still a gap.

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

Deploy Server