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

Annotations already cover read-only, idempotent, non-destructive and closed-world, so the safety profile is done. The description adds genuinely non-obvious behavior: result richness varies by source (official channels return outlet, section and a summary; digest items from other outlets return only a headline) and the corpus is Spanish-language. It stops short of describing result ordering or paging behavior.

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 action and corpus, then the return-field nuance, then the query/filter/timeline capabilities in one compact closing sentence. Dense but every clause carries information; no filler or repetition of the title.

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 and a 5-parameter schema at 40% coverage, the description does the heavy lifting by explaining result-field variation by source and timeline output shape. The remaining gap is operational: nothing on result ordering in the default mode, maximum result size, or pagination, which matters for an archive search capped at limit=100.

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 40%, so the description needs to carry weight, and it does: it tells the agent that 'q' is a Spanish full-text query, that from/to are a date range, and that 'timeline' produces oldest-first items with extracted events and per-month counts. It does not clarify 'limit' or restate the format constraint on 'to', leaving those 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?

States a specific verb and resource: 'Searches Guatemalan and Central American news items (daily digests and feeds)'. The domain is distinctive enough to separate it from search_bills, search_legal, search_research and the generic 'search', though no sibling is named explicitly. It also enumerates the returned fields (headline, date, link, outlet, section, summary), which sharpens what kind of resource this is.

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?

Offers usage hints ('Spanish full-text search', date-range filtering, and 'timeline: true traces how an event or story developed') but never states when to pick this over the generic 'search' tool or the other search_* siblings. The timeline guidance is the only real when-to-use cue, and there are no exclusions.

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