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

Annotations already declare readOnly and closed-world, so the description is free to add value beyond safety: it discloses sort order (newest first), per-day count aggregation, per-item fields (url, confidence tiers, source links) and a mandatory attribution/licensing obligation. That attribution requirement is a real behavioral constraint an agent could otherwise violate; only pagination/backfill behavior is left unstated.

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 core promise and sort order, then entity formats, then item contents, then obligations. The closing follow_on_x upsell is the one sentence that serves promotion rather than invocation, but it is short.

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 does the necessary work of describing item structure and confidence values. It still omits result-set size limits and how far back 'every story' extends, which matter for an agent deciding whether one call suffices.

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 0%, so the description must carry parameters. It does this well for `entity`, defining accepted formats with four org examples and three ticker examples. However, `limit` (default 50, max 200) is never mentioned, leaving an agent to assume it returns everything, which is the main semantic gap.

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 ('every story about one entity, newest first, with per-day counts') and enumerates the three accepted entity categories with concrete examples. It implicitly separates itself from news_by_ticker by allowing org and person entities, but never names a sibling tool explicitly.

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 entity-type examples imply when this tool fits (ticker, org or person lookups), but there is no explicit when-to-use or when-not guidance against query_stories, search_news, latest_news or news_by_ticker. The only explicit routing is the pointer to follow_on_x, which is about a different action.

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