Skip to main content
Glama
loosephoto

space-finder-mcp

by loosephoto
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

cadc_observations

Search CADC observation metadata for telescopes like Hubble and Gemini by object name or coordinates. Query public astronomical data without authentication.

Instructions

CADC（カナダ天文データセンター）の観測データを検索する（認証不要）。

HST(ハッブル)・ジェミニ望遠鏡・NEOSSat 等の観測メタデータを、
天体名または座標（ra/dec）で ADQL 検索する。

例:「ハッブルが撮ったNGC 300」「オリオン星雲の観測データ」「ジェミニの観測一覧」
パブリックメタデータは認証不要。画像ダウンロードは一部要認証。

Args:
    object_name: 天体名（例 "M31", "Orion", "NGC 300", "M104", "Sombrero", "HL Tau"）。
        座標指定より優先。内蔵テーブルに無い名前は **SIMBAD/NED（Sesame）で座標解決**し、
        和名（オリオン大星雲 等）も英語名に展開して解決する（推測では検索しない）。
    ra: 赤経（度）。object_name 省略時、dec と併用。
    dec: 赤緯（度）。
    radius: 検索半径（度, 既定 0.5）。
    telescope: 望遠鏡で絞り込み（例 "HST", "Gemini-North", "TESS"）。
    limit: 返す件数（既定 8、最大 20）。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
raNo
decNo
limitNo
radiusNo
telescopeNo
object_nameNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.25.2

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does well: it discloses that lookup is unauthenticated for public metadata but partially restricted for image download, that unresolved names are resolved via SIMBAD/NED (Sesame) with Japanese-name expansion and no guessing, and that results are capped (limit default 8, max 20). It does not describe the returned record structure or pagination, so it is strong but not exhaustive.

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

Conciseness4/5

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

Front-loaded with purpose, then scope, then examples, then per-argument semantics, so an agent can stop reading at any level. It is slightly long-winded in the object_name entry, where five example names plus the SIMBAD explanation could be trimmed, but every block still carries usable information.

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?

For a six-parameter tool with no annotations and no output schema, the description covers selection logic, auth requirements, resolution behavior, and result caps. The only real gap is what a returned observation record contains, though with no output schema that gap is not fully avoidable.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must compensate and it does: every one of the six parameters is defined with units (degrees), defaults (radius 0.5, limit 8), a max (20), value examples ('HST', 'Gemini-North', 'TESS'), and a precedence rule between object_name and ra/dec. This is exactly the semantic detail the bare schema lacks.

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 and resource ('CADCの観測データを検索する') and scopes it to concrete holdings (HST, Gemini, NEOSSat metadata) retrieved via ADQL by object name or coordinates. The example queries ('ハッブルが撮ったNGC 300', 'オリオン星雲の観測データ') make the intended use unmistakable and clearly separate it from generic image search siblings like search_space_images.

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 clear operational conditions: object_name takes precedence over coordinates, and ra/dec are only used together when object_name is omitted. Auth context ('パブリックメタデータは認証不要。画像ダウンロードは一部要認証') tells the agent when the tool works unauthenticated. It stops short of explicitly naming an alternative (e.g. alma_search or eso_seeing) for overlapping archive queries.

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

Deploy Server

Other Tools