Skip to main content
Glama

Dark moonless observing window

astro_dark_window
Read-onlyIdempotent

The genuinely dark, moonless observing window for a night: astronomical night intersected with the Moon being down, ranked across up to 62 nights with a trend. The right tool for "when should I stargaze / photograph the Milky Way / observe deep-sky objects". Location required. For plain twilight times use astro_sun.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tzNoIANA timezone like "Europe/Lisbon" to render event times in local time. Optional; a resolved place supplies its own timezone.
latNoLatitude in decimal degrees, north positive. Send lat and lon together.
lonNoLongitude in decimal degrees, east positive (Lisbon is about -9.14). Send lat and lon together.
dateNoNight to start from. ISO 8601 UTC date or datetime, e.g. "2026-08-06" or "2026-08-06T21:00:00Z". Or jd: followed by a Julian Day on the UT scale, e.g. "jd:2461000.5". On astro_positions, date may list up to 24 datetimes separated by commas, answered in the order sent. Omit for the current moment. Years 1700 to 2200 only; outside that range the API refuses with DATE_OUT_OF_RANGE because the ephemeris is not reliable there.
placeNoPlace name instead of lat/lon, as "City" or "City,CC" with an ISO country code, e.g. "Lisbon,PT". Resolved server-side; the response then carries a required GeoNames CC BY 4.0 credit in its attribution field, which must be preserved when shown.
nightsNoHow many nights to evaluate and rank. Default 1.
moon_illumination_maxNoTreat the Moon as tolerable below this illuminated fraction (0..1) even when up.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataYesThe best genuinely dark observing windows across a range of nights.
rightsNoEither unrestricted, or attribution_required when third-party place data was used. When attribution_required, the attribution line must be shown.
warningsNoMachine-readable notices about this answer. Present only when non-empty. Never changes whether the call succeeded.
attributionNoThe credit line to display verbatim when rights is attribution_required.
next_cursorNoPresent only when more rows exist. Send it back with the SAME start/end arguments as the first call to get the next page.
not_computedNoData this API deliberately does not serve, and why. Present only when the question touched such a field. An absence named here is information: treat it as "withheld", never as "none exists".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / date / description
      Previous value: -"Night to start from. ISO 8601 UTC date or datetime, e.g. \"2026-08-06\" or \"2026-08-06T21:00:00Z\". Omit for the current moment. Years 1700 to 2200 only; outside that range the API refuses with DATE_OUT_OF_RANGE because the ephemeris is not reliable there."New value: +"Night to start from. ISO 8601 UTC date or datetime, e.g. \"2026-08-06\" or \"2026-08-06T21:00:00Z\". Or jd: followed by a Julian Day on the UT scale, e.g. \"jd:2461000.5\". On astro_positions, date may list up to 24 datetimes separated by commas, answered in the order sent. Omit for the current moment. Years 1700 to 2200 only; outside that range the API refuses with DATE_OUT_OF_RANGE because the ephemeris is not reliable there."
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "description": "The MCP projection of a CycleCalcs v2 response: the answer, plus the provenance a caller needs to use it honestly.",
      +  "properties": {
      +    "attribution": {
      +      "description": "The credit line to display verbatim when rights is attribution_required.",
      +      "type": "string"
      +    },
      +    "data": {
      +      "additionalProperties": true,
      +      "description": "The best genuinely dark observing windows across a range of nights.",
      +      "properties": {
      +        "best_night_index": {
      +          "description": "Index into `nights` of the best one.",
      +          "type": "integer"
      +        },
      +        "high_latitude_caution": {
      +          "description": "True when latitude makes true darkness scarce or absent, so the ranking means less.",
      +          "type": "boolean"
      +        },
      +        "high_latitude_note": {
      +          "description": "The explanation when that caution is set.",
      +          "type": [
      +            "string",
      +            "null"
      +          ]
      +        },
      +        "method": {
      +          "description": "How darkness was defined and how nights were ranked.",
      +          "type": "object"
      +        },
      +        "nights": {
      +          "description": "Each night with its dark window and what the Moon does to it.",
      +          "type": "array"
      +        },
      +        "ranked": {
      +          "description": "Night indices best to worst.",
      +          "type": "array"
      +        },
      +        "summary": {
      +          "description": "The recommendation in brief.",
      +          "type": "object"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "next_cursor": {
      +      "description": "Present only when more rows exist. Send it back with the SAME start/end arguments as the first call to get the next page.",
      +      "type": "string"
      +    },
      +    "not_computed": {
      +      "description": "Data this API deliberately does not serve, and why. Present only when the question touched such a field. An absence named here is information: treat it as \"withheld\", never as \"none exists\".",
      +      "type": "array"
      +    },
      +    "rights": {
      +      "description": "Either unrestricted, or attribution_required when third-party place data was used. When attribution_required, the attribution line must be shown.",
      +      "type": "string"
      +    },
      +    "warnings": {
      +      "description": "Machine-readable notices about this answer. Present only when non-empty. Never changes whether the call succeeded.",
      +      "type": "array"
      +    }
      +  },
      +  "required": [
      +    "data"
      +  ],
      +  "type": "object"
      +}
  3. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds meaningful behavior beyond that: it intersects two conditions, ranks results across up to 62 nights, and includes a trend. It does not mention the DATE_OUT_OF_RANGE/1700-2200 constraint, but that lives in the schema.

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 tightly written sentences, front-loaded with the core behavior, then the use case, then the fallback sibling. Every sentence earns its place with no redundancy.

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 read-only ranked-list tool with an output schema and full schema coverage, the description supplies everything needed: what it computes, when to use it, the location requirement, and the alternative. Return values are rightly left to the output schema.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents lat/lon/place/tz/date/nights/moon_illumination_max in detail. The description confirms the location requirement and the up-to-62-night ranking, which is only marginal added value over the structured fields. Baseline 3 is appropriate.

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+resource (the dark moonless observing window) with precise scope: astronomical night intersected with the Moon being down. It explicitly distinguishes itself from the sibling astro_sun, so the agent can route correctly without opening schemas.

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?

Names the exact use cases ('when should I stargaze / photograph the Milky Way / observe deep-sky objects') and explicitly redirects to astro_sun for plain twilight times. Both when-to-use and the alternative are spelled out.

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.

Resources