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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower, yet the description adds real context: deduplication by grouping identical stories with source counts, a transparent rule-based score (relative source rank, multi-source presence, AI readership, time decay), and the explicit absence of article bodies. This is meaningful behavioral disclosure beyond the annotations, though it omits pagination/ordering stability details.

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?

The resource and scope are front-loaded, and most clauses carry information (sources, dedup, scoring factors, no-body caveat). The Korean/English duplication inflates length and repeats the same content, which is the main efficiency cost.

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?

With no output schema, the description usefully specifies what is returned (titles and original links only) and how results are ordered and scored, which is the key missing structured information. It is complete enough to call correctly, with only minor gaps around limit/window behavior and interaction with sibling search tools.

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 80%, so the schema already documents sort, source, and window values. The description restates the four ranking modes and the five sources, which mirrors the enum descriptions rather than extending them, and it says nothing about limit, window granularity, or query matching beyond what the schema shows. Baseline 3 is appropriate.

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 description names a concrete resource set (Korean government/public announcements: press releases, policy news, legislative notices, laws, Æfact checks) and the action (deduplicate across sources, rank into one list), so an agent knows exactly what it produces. It also draws a boundary against judgment tools by stating '판정이 아니며, 판정은 check_url 에 있습니다', though the referenced tool is not among the listed siblings and no contrast with search_articles or what_changes is drawn.

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?

It gives clear conditions for use: pull currently-available aggregated news, with sort modes for hot/new/ai/talk, and it explicitly states the output is titles plus original links with no body — implicitly routing body needs elsewhere. It also names an alternative (check_url) for judgment, but does not say when to prefer this over search_articles or what_changes.

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