gcn_alerts

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

With no annotations present, the description carries the full burden and does disclose key behavior: authentication is not needed, date filtering is done on UTC dates, and circular_id returns one full body instead of a list. It does not mention rate limits, failure behavior, or the fields present in returned circulars, which are the remaining gaps.

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?

Purpose is front-loaded in one sentence, followed by grouped example utterances, a compact Args block, and a closing output instruction. Nothing is redundant, though the closing presentation note is an instruction rather than tool-scoping information.

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 four-parameter, unauthenticated read tool with no output schema and no annotations, the description covers mode selection, filtering semantics, and limits well enough to call it correctly. The main missing piece is what a returned circular actually contains (title, submitter, body, link), which the agent must discover empirically.

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 description coverage is 0%, yet the Args block fully documents all four parameters: days range 1–60 with default 7 and UTC semantics, query with real keyword examples and the omitted-means-all behavior, circular_id with a format example and its mode-changing effect, and limit default 25 / max 100. This compensates completely for the bare schema.

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?

The first sentence names a specific verb and resource — returning NASA GCN Circulars for transient astronomical events — and adds a scope qualifier (no authentication required). It is clearly distinct from sibling tools like astronomy_news or space_literature_search because it names the exact data source.

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 example queries ("直近1週間のGRB速報", "重力波の続報") show concrete situations where the tool applies, and the circular_id argument is explicitly described as switching from list mode to single-record retrieval. There is no explicit when-not-to-use guidance or named alternative tool, which keeps it below a 5.

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