Get the latest observed weather conditions for a US location by latitude/longitude, from the nearest NWS observation station: temperature, humidity, wind, and text description.
| Name | Required | Description | Default |
|---|---|---|---|
| lat | Yes | Latitude in decimal degrees, e.g. 36.1867. US coverage only (National Weather Service). | |
| lon | Yes | Longitude in decimal degrees, negative in the western hemisphere, e.g. -94.1288. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral disclosure burden. It does disclose that the operation is read-only, the data source (NWS), and the output fields. However, it does not mention units, staleness, error behavior, or what happens when no station is near, which are relevant but not critical for invocation.
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?
The description is a single front-loaded sentence that packs in the verb, resource, scope, source, and outputs without any filler or redundant phrasing.
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 simple read-only tool with two well-documented parameters and no output schema, the description is nearly complete: it explains what it returns and from where. It lacks units and edge-case behavior, but these are not required to invoke the tool correctly.
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 description coverage is 100%, and both lat and lon already have detailed descriptions, so the baseline is 3. The description adds no new parameter-level meaning beyond repeating the US location constraint already present in the schema.
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?
The description names a specific verb ('Get'), a clear resource ('latest observed weather conditions'), and a specific scope ('US location by latitude/longitude, from the nearest NWS observation station'). It also enumerates the returned fields, making it immediately distinguishable from sibling tools like weather_forecast (observed vs forecast) and weather_alerts.
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?
The description implies its use case: current observed weather for a US lat/lon. However, it does not explicitly name alternatives or state when not to use it, leaving the agent to infer the difference from weather_forecast based on the word 'observed' and the tool name.
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.
Each tool targets a distinct query type: seismic events, elevation, geocoding, weather alerts, current observations, and forecasts. There is no meaningful overlap, and the weather_current/weather_forecast/weather_alerts trio is clearly separated by description.
Tool names are lowercase and simple, with a clear weather_ prefix grouping the NWS-related tools. The main minor deviation is geocode being verb-style while earthquakes and elevation are noun-style, but the overall pattern remains predictable.
Six tools is a well-scoped size for a weather and geo intelligence server. Each tool earns its place and together they cover the major natural query categories without unnecessary overlap or bloat.
The server supports the core workflow of taking a text location, geocoding it, and then getting elevation, current weather, forecast, or earthquake data. Minor gaps like missing reverse geocoding or location-based alert search are workable but not critical.