capabilities

Get the latest US weather observation with its age (NWS)

weather_us_observation

Read-onlyIdempotent

Latest surface observation from the nearest National Weather Service station to a US coordinate, with the station identity, the observation time (observed_at), its age in seconds and an is_stale flag. Station observations are reported roughly every 20-60 minutes, so this is the most recent measurement, not a real-time reading. Use when: What was the most recently observed temperature at these US coordinates? Not for: You need a prediction rather than a measurement - use weather.us.forecast. Related: weather_us_forecast; weather_us_alerts. Price: USD 0.003/call (x402), 0.002 (account key).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`lat`	Yes	Latitude in decimal degrees (WGS84). Rounded to 4 decimal places before the National Weather Service lookup.
`lon`	Yes	Longitude in decimal degrees (WGS84). Rounded to 4 decimal places before the National Weather Service lookup.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	Yes	Capability output; full JSON Schema at https://api.eckari.com/v1/capabilities/weather.us.observation
`meta`	Yes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed7 schema fields changedAug 18, 2026

removedOutput schema / properties / data / additionalProperties
```
Removed value: -false
```

addedOutput schema / properties / data / description

Added value: +"Capability output; full JSON Schema at https://api.eckari.com/v1/capabilities/weather.us.observation"

removedOutput schema / properties / data / properties

Removed value: -{
-  "age_seconds": {
-    "description": "Whole seconds between observed_at and the time this response was produced. Always inspect this before treating the reading as current.",
-    "minimum": 0,
-    "type": "integer"
-  },
-  "barometric_pressure_pa": {
-    "description": "Station barometric pressure in pascals. Null when the station omits the value or its quality control rejected it (NWS qualityControl X = failed or Q = questionable).",
-    "type": [
-      "number",
-      "null"
-    ]
-  },
-  "cloud_layers": {
-    "description": "Reported cloud layers, lowest first, exactly as published by the station.",
-    "items": {
-      "additionalProperties": false,
-      "properties": {
-        "amount": {
-          "description": "METAR cloud amount code - one of CLR / FEW / SCT / BKN / OVC / VV.",
-          "type": [
-            "string",
-            "null"
-          ]
-        },
-        "base_m": {
-          "description": "Cloud base height above ground in metres.",
-          "type": [
-            "number",
-            "null"
-          ]
-        }
-      },
-      "required": [
-        "amount",
-        "base_m"
-      ],
-      "type": "object"
-    },
-    "type": "array"
-  },
-  "dewpoint_c": {
-    "description": "Dewpoint in degrees Celsius (2 decimal places). Null when the station omits the value or its quality control rejected it (NWS qualityControl X = failed or Q = questionable).",
-    "type": [
-      "number",
-      "null"
-    ]
-  },
-  "is_stale": {
-    "description": "True when age_seconds exceeds 10800 (3 hours). The observation is still returned; the flag says it is old.",
-    "type": "boolean"
-  },
-  "observed_at": {
-    "description": "Time the observation was taken, as reported by the station (ISO 8601 UTC). This is not the request time.",
-    "type": "string"
-  },
-  "precipitation_last_hour_mm": {
-    "description": "Precipitation in the last hour in millimetres. Null when the station does not report it or its quality control rejected it (NWS qualityControl X = failed or Q = questionable).",
-    "type": [
-      "number",
-      "null"
-    ]
-  },
-  "relative_humidity_pct": {
-    "description": "Relative humidity as a percentage (2 decimal places). Null when the station omits the value or its quality control rejected it (NWS qualityControl X = failed or Q = questionable).",
-    "type": [
-      "number",
-      "null"
-    ]
-  },
-  "station": {
-    "additionalProperties": false,
-    "properties": {
-      "distance_km": {
-        "description": "Great-circle distance in kilometres (2 decimal places) from the coordinate you asked about to the station's published position, computed by Eckari on a spherical earth. It is not the National Weather Service's own distance figure, which is measured from the forecast grid point rather than your point. Null when the station publishes no coordinates.",
-        "type": [
-          "number",
-          "null"
-        ]
-      },
-      "id": {
-        "description": "NWS station identifier (for example KDCA).",
-        "type": "string"
-      },
-      "name": {
-        "description": "Station name as published by NWS.",
-        "type": [
-          "string",
-          "null"
-        ]
-      }
-    },
-    "required": [
-      "id",
-      "name",
-      "distance_km"
-    ],
-    "type": "object"
-  },
-  "temperature_c": {
-    "description": "Air temperature in degrees Celsius (2 decimal places). Null when the station omits the value or its quality control rejected it (NWS qualityControl X = failed or Q = questionable).",
-    "type": [
-      "number",
-      "null"
-    ]
-  },
-  "text_description": {
-    "description": "Station's own summary phrase such as Mostly Cloudy.",
-    "type": [
-      "string",
-      "null"
-    ]
-  },
-  "visibility_m": {
-    "description": "Horizontal visibility in metres. Null when the station omits the value or its quality control rejected it (NWS qualityControl X = failed or Q = questionable).",
-    "type": [
-      "number",
-      "null"
-    ]
-  },
-  "wind_direction_deg": {
-    "description": "Wind direction in degrees clockwise from true north. Null when variable, when the station omits the value, or when its quality control rejected it (NWS qualityControl X = failed or Q = questionable).",
-    "type": [
-      "number",
-      "null"
-    ]
-  },
-  "wind_gust_kmh": {
-    "description": "Wind gust in kilometres per hour. Null when the station omits the value or its quality control rejected it (NWS qualityControl X = failed or Q = questionable).",
-    "type": [
-      "number",
-      "null"
-    ]
-  },
-  "wind_speed_kmh": {
-    "description": "Wind speed in kilometres per hour (2 decimal places). Null when calm, when the station omits the value, or when its quality control rejected it (NWS qualityControl X = failed or Q = questionable).",
-    "type": [
-      "number",
-      "null"
-    ]
-  }
-}

removedOutput schema / properties / data / required

Removed value: -[
-  "station",
-  "observed_at",
-  "age_seconds",
-  "is_stale",
-  "cloud_layers"
-]

addedOutput schema / properties / meta / properties / attribution_url
```
Added value: +{
+  "format": "uri",
+  "type": "string"
+}
```
addedOutput schema / properties / meta / properties / retrieved_at / format
```
Added value: +"date-time"
```

addedOutput schema / properties / meta / required

Added value: +[
+  "capability",
+  "version",
+  "retrieved_at",
+  "source",
+  "freshness",
+  "request_id"
+]

First observedAug 18, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds value by explaining the polling frequency ('every 20-60 minutes'), that it's 'the most recent measurement, not a real-time reading', and the is_stale flag – all behavioral insights beyond the annotations.

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?

Three well-structured sentences: first explains what the tool returns, second provides behavioral context, third gives usage guidance and pricing – no wasted words, front-loaded with key information.

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?

Given the tool has 2 well-documented params, a complete output schema, and full annotation coverage, the description elegantly fills gaps by explaining staleness, observation frequency, and use-case boundaries – fully sufficient for an agent to select and invoke correctly.

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% with detailed descriptions for lat and lon (including rounding to 4 decimal places and WGS84 coordinate system). The description adds context by linking parameters to the nearest station lookup, but does not repeat schema information; a minor improvement would be a short mention of rounding impact.

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 uses a specific verb 'Get' with a clear resource 'latest surface observation' from a source 'nearest National Weather Service station' and lists key output fields (station identity, observed_at, age, is_stale). It distinguishes itself from siblings by mentioning US coordinates and the time-bound nature of observations.

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 states when to use ('What was the most recently observed temperature at these US coordinates?') and when not to ('Not for: You need a prediction rather than a measurement'), with direct sibling tool names (weather_us_forecast and weather_us_alerts) and pricing context, providing comprehensive guidance.

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

All capabilities 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

Disambiguation4/5

Tools are largely distinct, targeting specific entities (UK company, US company, domain, LEI, FX, location, parcel, weather) or sub-aspects (e.g., accounts vs. charges vs. directors). Overlap exists between company.uk.profile and company.uk.status (both contain status info, but the latter is cheaper and focused). Also, company.uk.filings and company.us.filings_latest could be confused if an agent generalizes 'filings' across jurisdictions.

Naming Consistency5/5

All tools follow a consistent pattern: domain_entity_subject (e.g., company_uk_accounts, domain_expiry, weather_us_alerts). Underscores and lower case are used throughout. Verbs are implied by the noun (e.g., 'search' for lookup, 'detect' for identification). No mixed conventions or unpredictable names.

Tool Count4/5

24 tools is on the high side but still reasonable for a general-purpose data server spanning multiple domains (company, domain, entity, fx, location, parcel, weather). Each domain gets a cohesive set, and the documentation justifies each tool. Could be slightly leaner if some niche tools (e.g., domain_expiry vs. registration) were merged, but overall scoping is acceptable.

Completeness4/5

Each domain offers good coverage: UK company tools cover CRUD-like operations (profile, status, search, filings, charges, directors, owners, registered office); similarly for US companies (profile, filings, resolve, latest filings). Weather has forecast, observation, alerts. Parcel only detects carrier (no tracking). Missing features like advanced filtering on company filings or less common domains, but core workflows are covered.

Resources

Need Help?