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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds real behavior: accent-insensitive matching, semantic fallback ordering, empty-query ordering, and cursor-based pagination via 'next'. The only weak spot is that it advertises a 'match: semantic' parameter that is not in the input schema, which could send the agent looking for a knob that does not exist.

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?

Four front-loaded sentences: capability, matching strategy, empty-query edge case, return shape. Dense with no filler. The parenthetical 'match: semantic' is the one sentence fragment that costs clarity rather than buying it.

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 11 optional parameters and an output schema, this covers what the agent needs: what is searchable, how matching degrades, what an empty query does, and how to page. The dangling 'match' reference is the only gap, and since the output schema carries the return contract, describing results here is a minor redundancy rather than a flaw.

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?

Adds meaning beyond the 73%-covered schema: bilingual/accent-insensitive search, 'every tag must be present' semantics, and date-range phrasing. Against that, the 'match: semantic' reference maps to no declared parameter, and cursor/limit/sort behavior is left entirely to 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?

Opens with a specific verb and resource ('Search every article and news brief') and enumerates the facets it searches, so the agent knows this is the corpus-wide discovery entry point rather than a by-id lookup. It never names a sibling such as fetch or related, so the differentiation is implicit rather than stated.

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?

Gives concrete invocation guidance: an empty query returns the newest pieces, and semantic matching is the fallback 'when keywords find few'. That tells the agent both the zero-result escape hatch and the degradation path, but it does not say when to prefer this over fetch, related, or timeline.

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