Retrieve Roscosmos open-data STAC collections, traversing up to instrument or processing levels, to identify available Russian satellite datasets without authentication.
Roscosmos オープンデータ STAC のコレクション一覧を返す（認証不要）。
例:「ロシアの気象衛星の公開データ」「Elektro-L の全球画像コレクション」
Args: level: 辿る深さ（1=最上位のみ、2=観測機器まで〈既定〉、3=処理レベルまで。最大 3）。
| Name | Required | Description | Default |
|---|---|---|---|
| level | No |
Changes observed during successful MCP inspections.
v0.41.4Input schema / properties / level / titleRemoved value: -"Level"Input schema / titleRemoved value: -"roscosmos_collectionsArguments"v0.39.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and does add value by declaring '認証不要' (no authentication required) and explaining that the level parameter controls how deep the returned collection tree goes. However, it says nothing about output shape, result volume, or whether deep traversal is expensive, so a caller can't predict cost or response structure.
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?
Front-loads the purpose and auth status, then adds two short illustrative examples, then the argument spec. Every line contributes, and there is no filler.
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 one-parameter, read-only listing tool with no output schema or annotations, the description covers purpose, auth, and the full enumeration of the level parameter's semantics, which is enough to call it correctly. It falls short of 5 only in not hinting at response size or how the traversal affects output.
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 coverage is 0%, but the description fully compensates for the single parameter: it defines each level value (1=top only, 2=instruments/default, 3=processing level) and states the max is 3. The only minor gap is not clarifying what 'processing level' entries actually represent.
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?
States a specific verb (returns a list) and resource (Roscosmos open-data STAC collections), and the parenthetical provider name distinguishes it from copernicus_collections, inpe_collections, and the sibling roscosmos_search without needing to open any schema. The examples anchor the resource concretely.
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 examples ('Russian meteorological satellite open data', 'Elektro-L global imagery') imply a discovery use case, but the description never explicitly says when to prefer this over roscosmos_search or the generic stac_collections, and gives no when-not guidance. Usage is inferable rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.