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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed-world scope, so the safety profile is covered. The description adds genuinely non-structured information: that these are multi-day cases, the 30-day recency window, and the returned facets (resumo, envolvidos, países). It stops short of describing ordering or result caps, which keeps it below a 5.

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?

The Portuguese sentence is front-loaded and information-dense, with scope stated before examples. The full English translation repeats the same content verbatim, roughly doubling length without adding any new detail, and the trailing examples are only loosely tied to the preceding claim.

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 does not need to document return values, and annotations already carry the safety profile; the remaining gaps are minor. For a zero-required-parameter listing tool the coverage is solid, though pagination, ordering, and whether the 30-day window is a hard retrieval limit are left unresolved.

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% and the single enum parameter already documents active vs archived, so the baseline of 3 applies. The description restates the same active/archived concept in prose without adding new per-parameter meaning, such as what "archived" implies for case state or recency.

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 names a concrete resource ("Casos em desenvolvimento ... hacks, processos e regulações") and its scope (multi-day, active or archived within 30 days, returned with summary, involved parties and countries). This clearly separates a themed-case listing from a story-level tool, but it never names a sibling such as buscar or get_tema, so the differentiation remains implicit.

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?

The two quoted example questions ("Quais casos de cripto estão em aberto no Brasil?", "Temas arquivados do mês") give implied usage scenarios, which is better than nothing. However, there is no explicit statement of when to prefer this over buscar, get_tema or ultimas_historias, and the phrase "ativos ou arquivados nos últimos 30 dias" is ambiguous about whether the 30-day window binds both statuses or only archived items.

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