news_feed

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

With no annotations supplied, the description carries the full behavioral burden and it partially covers it: it discloses ordering ('strongest links first') and that each result carries a ranking code plus a reason. It does not state that this is a read-only operation, how results are capped or paginated, or whether an empty profile yields an error versus an empty list. Adequate but with real gaps for a zero-annotation tool.

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 short sentences with the ranking behavior front-loaded and the delegation hint second; nothing is padded. The clipped 'since: YYYY-MM-DD' fragment is efficient but reads as a note rather than prose, which slightly weakens the structure.

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?

An output schema exists, so return values needn't be described, and the description does note the per-item reason field that a caller will see. However, for a three-parameter tool with no annotations and no schema documentation, leaving `top` and the meaning of profile_id's 'subject' role unexplained is a meaningful omission.

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 description must compensate for all three parameters. It explains the format of `since` (YYYY-MM-DD) and loosely identifies `profile_id` as 'the subject', but `top` — the result limit, defaulting to 10 — is never mentioned, leaving a caller to infer whether it is a count, a scope, or something else.

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 states a specific resource and scope: stored news concerning a subject, ranked strongest-links-first with a reason per item. It also implicitly separates itself from analyze_news by naming that tool for follow-up depth. It stops short of a clean verb-led statement ('Which stored news concern the subject' is a fragment), but the retrieval purpose is unambiguous.

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 concrete routing guidance: use analyze_news on an event_id taken from this list to get full insight, which tells the agent this is the shallow discovery step and that tool is the depth step. It does not state exclusions (e.g. when to prefer list_events or search_research instead), so the when-not half of the guidance is missing.

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