novidades

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

With no annotations supplied, the description carries the full burden and does so: it discloses the hidden side effect (the checkpoint advances and messages won't repeat unless marcar=false), the server-side filtering by role, and why a group may return empty despite new messages. It even names a return field (`ignoradas_por_papel`) that explains the empty case, which is exactly the kind of behavior an agent cannot infer from structured fields.

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 filter caveat, and every clause carries information — the empty-result warning, the trigger, the checkpoint side effect, and the scope parameter. The all-caps emphasis and dash-separated clauses make it slightly dense to parse, but nothing is wasted.

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 two-parameter read-with-side-effect tool with no annotations and no output schema, the definition covers the trigger, the filtering semantics, the state mutation, and the notable return field. The only gap is the general shape of the returned message payload, which the agent must discover by calling it.

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 both parameters are already documented. The description restates their effect in context ('Com grupo, restringe a um chat'; 'a menos que marcar=false'), which reinforces the checkpoint consequence but adds little syntax or edge-case detail beyond 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 ('Puxa as mensagens novas dos chats marcados com alerta desde a última vez que você viu') and immediately pins down the scope with a filter rule (only CLIENT messages). It also differentiates itself from the sibling ler_mensagens by naming it as the fallback when the filtered result comes back empty.

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 an explicit trigger ('Use ao ser notificado de mensagem nova') and routes the agent to ler_mensagens for the internal-group edge case where this returns nothing. It stops short of stating when not to call it at all (e.g. for own/team messages), but the filter note effectively conveys that limitation.

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