usgs_earthquakes$0.002 per call — Recent earthquakes from the USGS GeoJSON feed (no API key). Returns magnitude, place, time, depth and coordinates for each event. Params: period = hour|day|week (default day); minmag = minimum magnitude (default 0); limit = max events (default 20).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max events returned (default 20) | |
| minmag | No | Minimum magnitude (default 0) | |
| period | No | hour | day | week | month (default day) |
Changes observed during successful MCP inspections.
Input schema / properties / limitAdded value: +{
+ "description": "Max events returned (default 20)",
+ "type": "number"
+}Input schema / properties / minmagAdded value: +{
+ "description": "Minimum magnitude (default 0)",
+ "type": "number"
+}Input schema / properties / periodAdded value: +{
+ "description": "hour | day | week | month (default day)",
+ "type": "string"
+}Input schema / properties / qRemoved value: -{
- "description": "JSON or key=value input for the tool",
- "type": "string"
-}Input schema / requiredAdded value: +[]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does meaningful work: it discloses the data source (USGS GeoJSON), that no API key is needed, and the per-call cost of $0.002. It stops short of stating rate limits, pagination behavior, or how fresh the feed is.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Cost and source are front-loaded, followed by the payload and parameters, in a compact multi-clause form with no filler. The parameter restatement is somewhat duplicative of a schema that already documents every field with defaults.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a no-auth, three-optional-param read tool with no output schema, the description supplies source, cost, auth posture, parameter defaults, and the shape of each returned event. Only freshness/rate-limit details are absent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is already 100%, so the baseline is 3, but the description's param list actively narrows the enum: it says 'period = hour|day|week' while the schema also permits 'month'. An agent relying on the prose alone would miss a valid option, which is worse than adding nothing.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Recent earthquakes from the USGS GeoJSON feed') plus the exact fields returned (magnitude, place, time, depth, coordinates). No sibling tool overlaps this domain, so the agent can route to it unambiguously.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is only implied by the parameter defaults (period, minmag, limit); there is no explicit statement of when to reach for this tool versus alternatives, nor any exclusions. For a simple single-purpose read tool with no comparable siblings, that is minimally adequate rather than strong.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.