Metis · News Radar — Get Briefing Coverage

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

No annotations exist, so the description carries the full disclosure burden. It does explain the meaningful hidden behavior – that threads persist across days, can be surfaced once and then deliberately held quiet (cooldown), which is non-obvious and valuable. However, it never states that this is a read-only, side-effect-free listing (an agent must infer it from 'Show'), nor anything about result volume or cost despite potentially returning many threads.

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 primary capability is front-loaded in sentence one, with motivation and mechanism following in a sensible order, and the Args/Returns blocks are scannable. The middle paragraph explaining story threads is a touch discursive for a tool that already has an output schema documenting the per-thread fields.

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 2-parameter, non-destructive read tool with an output schema, the description covers intent, both parameters, and the conceptual model of threads and cooldowns. It even previews the return payload (size, age, may-lead, quiet duration, angles used) despite the output schema existing. The remaining gap is the absence of any explicit read-only / no-side-effect statement given that no annotations are supplied.

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% – both parameters carry only a title and default – so the description must compensate, and it largely does: `days` is defined as the window of news activity, and `show_all` is clarified as including single-item threads with the default state described as 'recurring only'. What is missing is any note on how the two interact (e.g. whether show_all widens beyond the days window).

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 gives a concrete verb and resource ('Show which news stories the briefings have covered, and what is on cooldown') and the 'why didn't today's brief mention X?' framing pins down the intent precisely. It also defines the underlying unit (story threads grouping items into a running story), so the agent knows what a row represents. It stops short of naming a sibling (e.g. get_missed_news, get_news_briefs) as the contrasting tool, which keeps it at 4 rather than 5.

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?

Two explicit user-questions are given as the calls this tool answers, which is clear usage context for an agent deciding whether to invoke it. There is no statement of when *not* to use it and no named alternative among the many news/brief siblings, so it lands just below the top band.

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