news_brief

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

With no annotations, the description carries the full behavior burden and does well: it discloses the cost model (one agent run per item, so latency and expense scale with top), a hard cap of top ≤ 5, and output ordering (highest impact first). It says nothing about the permissions or scope of the underlying profile, but the cost and ordering traits are the operationally important ones here.

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?

Two sentences, front-loaded with what the tool produces and immediately followed by the differentiator versus news_feed. Every clause carries information; nothing is redundant.

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 two-parameter tool with an output schema, the description covers what is returned in human terms (paragraphed, agent-explained items, impact-ordered), the cost profile, and the argument cap. The only real gap is the unexplained profile_id/'subject' relationship.

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%, so the schema documents neither parameter beyond its type and default. The description partially compensates by adding a real constraint the schema omits (top ≤ 5, which is not encoded as a maximum) and by explaining that output is ordered by impact, but profile_id is never mentioned or tied to 'subject'.

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 action (pull the strongest news for a subject, each turned into an agent-written paragraph, ordered by impact) and contrasts itself with news_feed on cost. It is clearly distinguishable from siblings like news_feed and analyze_news, though the vague word 'subject' leaves the reader mapping it onto profile_id themselves.

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?

'Slower than news_feed: one agent run per item' gives an explicit cost comparison against a named sibling, which is exactly the signal an agent needs to pick between the fast feed and the expensive brief. It stops short of stating the positive selection condition (e.g. 'use when you need per-item explanation'), so it is context rather than a full when/when-not rule.

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