listar_recentes

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds real behavior beyond them: newest-to-oldest ordering, future events/conferences included up to `dias` ahead, the `total`-vs-page distinction, the `tem_mais` pagination signal, and a prompt-injection warning about third-party content.

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 purpose, then a structured Args block. It is longer than typical but every section (ordering, return fields, per-param semantics, safety note) earns its place; only the return-field enumeration mildly overlaps the output schema.

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?

For a 6-param paginated listing tool with no required args, the description covers defaults context (dias window, limite/pagina bounds), pagination semantics, field contents, and a safety caveat. With an output schema and annotations already present, nothing an agent needs to call it correctly is missing.

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 carries the full burden and does: it explains every one of the six params, expands the `tipos` enum (including that episodio=podcast and repo=code repository), and clarifies that escopo applies only to news/eventos/conferências and that few items carry especialidade.

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 ("Lista") plus resource ("o que saiu de mais recente na base do IA.med sobre IA na medicina") and scope. It also names the sibling abrir_item (for more detail) and buscar (for topic search), so the agent can distinguish it without opening any 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?

Gives conditional routing: use abrir_item for the full item, and "se vier pouco, use buscar com o tema" when specialty filtering yields few results. It stops short of an explicit when-to-use statement (e.g., browse-by-recency vs. keyword search), so it is clear context but not a full when/when-not matrix.

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