Search news across sources

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the description only needs to add context, and it does: it says results are limited to what is currently in the feeds, and that failed sources or sources missing the requested category surface under an `errors` key. Since there is no output schema, that partial return-shape disclosure is valuable, though it doesn't say what the success payload looks like.

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?

Three short sentences, each doing distinct work: purpose plus scope, error behavior, and sibling routing. The scope caveat is front-loaded where it matters most, and 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?

With four fully documented parameters, no output schema, and annotations covering safety, the description supplies the remaining essentials: the non-archive scope, the `errors` key, and the routing to nw_tech_news. A brief note on result ordering or deduplication across sources would close the last gap.

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 100%, so query semantics (all keywords must match), limit ordering (newest first, 1-15), empty sources = all, and category slugs from nw_list_sources are already documented. The description only adds the errors behavior tied to the category parameter, which is marginal beyond the schema.

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 opens with a specific verb and resource: search recent headlines across several sources for a keyword, plus an explicit scope limit (current feeds, not an archive). That distinguishes it from nw_tech_news, but it doesn't differentiate it from nw_latest, nw_latest_all, or nw_article, which it overlaps with by searching headlines.

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 a clear condition for use (current feed stories, not archive retrieval) and explicitly routes technology queries to nw_tech_news. It offers no guidance, though, on when to use this rather than nw_latest or nw_latest_all, which is the harder choice for an agent.

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