Metis · News Radar — Mark Brief Read

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

With no annotations, the description carries the load and does disclose the meaningful side effect: story threads go on cooldown for the *next* briefs, and this is the only mechanism that silences them. It does not cover idempotency (calling twice) or what happens if no brief exists for the given date, so it falls short of a full behavioral contract.

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-loaded with the action and its effect, then the rationale, then params. The middle paragraph is slightly redundant with the first line, but it carries the non-obvious invariant about unread briefs, so it earns most of its space.

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?

Both parameters, the default behaviors, and the return value ('confirmation, plus which threads that brief had covered') are documented, so an agent can call it and interpret the result. Missing only edge-case behavior such as an unknown date or an already-read brief.

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%, but the description fully compensates: date is 'YYYY-MM-DD of the brief. Empty = today' and period is 'daily, weekly or catchup. Default daily.' That is exactly the enum values and default semantics the schema leaves undocumented.

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 and resource ('Mark a briefing as read') plus the downstream effect ('its story threads go quiet'). The resource is clearly the brief itself, which separates it from the sibling mark_publications_read and from get_news_briefs.

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?

Gives explicit trigger conditions: 'when you have delivered a briefing to the researcher in conversation, or when they say they have read it.' It also supplies the inverse constraint — a brief that was generated but never read must not silence anything — which tells the agent when not to call it.

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