Skip to main content
Glama

sky_map_with_satellites

Generate a sky map overlaying planets and artificial satellites for a chosen place and time, using JPL and CelesTrak data. Choose simple or accurate rendering.

Instructions

東京(または指定地)の空に太陽系の惑星と人工衛星を重ねた図を返す(認証不要)。

例:「東京の空に惑星と人工衛星を重ねた図」「今見えるISSを星空マップで」「木星はどこに見える?」
天体位置は JPL de421 + Skyfield、衛星位置は CelesTrak TLE + SGP4 で実測計算。

学生・観賞用途では視認性の高い Pillow 版(既定)を推奨。正確な座標プロットが必要な場合は
matplotlib 版も選択できる。

engine で描画方法を選択:
  - "simple"(既定):   Pillow による実写背景の簡易合成。惑星を種類別の色アイコンで
    大きく・明瞭に描き、学生が見やすい見た目重視の画像。
  - "accurate":       matplotlib による正確な星図。座標グリッド・軌道予測線を精確表示
    (科学・教育の詳細用途向け)。マーカーの色・光背・土星の環・木星の縞・火星の極冠・
    名札・凡例は simple 版と同じ指定色(_PLANET_VISUAL / _C_*)から作る。
画像は content に base64 インライン表示、座標は structuredContent に JSON。

Args:
    place: 観測地(例 "東京","大阪","new york")。lat/lon 指定時は無視。省略時は東京。
    lat: 観測地の緯度。lon と併用時は place より優先。
    lon: 観測地の経度。
    when: 観測時刻 ISO8601(例 "2026-09-09T11:00:00Z")。省略時は現在時刻。
    engine: "simple"(既定/Pillow) / "accurate"(matplotlib)。

インライン画像を表示できないハーネス(CLI系・Android系の codex / opencode など)向けに、
content の先頭へ「🖼️ [生成した画像を開く(…)](file:///…) | 保存先: `…`」という
アイコン付きリンクを必ず出します(画像は %LOCALAPPDATA%\Temp\space_finder_mcp\out に
保存し、同じパスを structuredContent.image_path にも入れます)。
回答時はこのリンクをそのまま提示してください(画像が描画されない環境では唯一の導線)。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
latNo
lonNo
whenNo
placeNo
engineNosimple

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.25.2

TDQS

A4.2/5.0
Behavior4/5

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

No annotations, so the description carries the burden. It discloses computed data sources (JPL de421 + Skyfield, CelesTrak TLE + SGP4), no-auth requirement, inline base64 output, temp file path, and the link behavior for harnesses that can't render images. Lacks error handling or rate-limit notes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded core purpose, but the body is long and mixes Japanese and English, with duplication around engine behavior and the link generation. Some content could be trimmed.

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?

Covers all parameters, default behavior, output format, and fallback link for non-rendering harnesses. Missing an output schema means the description must explain return values, which it does partially (base64 inline, structuredContent JSON).

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 0%, so the description lists all five parameters with meaning, allowed values for engine, default for place and when, and precedence rules (lat/lon over place, place ignored when lat/lon given).

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 (returns a diagram) and resource (sky map overlaying solar-system planets and satellites), with a concrete example list. It clearly distinguishes itself from siblings like iss_now and solar_system_now by combining both in one rendered image.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives example queries and recommends the Pillow engine for students/observation, but doesn't explicitly say when NOT to use this versus iss_now or solar_system_now for a specific need.

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