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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered structurally. The description adds genuinely useful behavior beyond that: results are relevance-ranked, they contain summaries plus canonical URLs, and an empty list has a definite meaning the agent must not paper over. It omits nothing important, though it doesn't discuss latency or result-count behavior beyond the schema.

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 tightly written sentences: capability and scope first, then differentiation from today-only lookup, then the empty-result contract. Every sentence carries a distinct, load-bearing instruction with no filler.

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 an output schema present, the description needn't enumerate return fields, and it still summarizes them (summaries plus canonical URLs). Combined with rich annotations and 100% schema coverage, all four parameters accounted for, and the failure-mode instruction included, an agent has everything needed to call this correctly.

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 100%, so days, limit, category, and query are all self-documented in the schema, which sets the baseline at 3. The description echoes the query semantics ('topic, theme, or news event') but adds no format, syntax, or interaction guidance for the filter parameters beyond what the schema already states.

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 verb (semantically search) plus resource (SkimNews' archive of 47,000+ summarised stories) and scope (by topic, theme, or news event, ranked by relevance). It explicitly contrasts with the sibling-driven default of only-today coverage, so an agent can distinguish it from get_top_stories without opening a schema.

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 names when to reach for this tool ('find coverage of a subject across SkimNews' history rather than only today') and prescribes the correct behavior on failure ('an empty result list means SkimNews has not covered that topic — say so rather than substituting unrelated stories'). That is an explicit when-to-use plus an exclusion rule, not just implied context.

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