filtrar

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

Annotations already cover read-only, idempotent, and closed-world behavior, so safety is established. The description adds real behavioral context beyond the annotations: the classification source ("classificação automática local (Laya)") and the fact that no-arg calls trigger discovery output. It does not, however, mention anything about the 'limite' truncation 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?

Three tightly packed sentences: purpose first, then the no-arg discovery behavior, then the property/value vocabulary and a concrete example. Every sentence earns its place and the most important routing information is front-loaded.

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, return values need not be described, and annotations cover the safety profile. The description supplies purpose, dual usage modes, filter vocabulary, and an example, so an agent can invoke it correctly. The only gap is the undocumented 'limite' parameter.

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 must carry the full parameter burden. It compensates well for 'propriedade' and 'valor' by enumerating available properties and their values (tipo, tem_pendencia, tem_decisao) and showing positional use in the example, but it never explains 'limite' or its default of 30.

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 states a specific verb+resource: it filters notes ("Filtra notas") using the local automatic classification (Laya), and explicitly contrasts itself with reading each note one by one ("sem precisar ler cada uma"). This makes it distinguishable from siblings like 'ler'. However, it never contrasts itself against 'buscar', the closest sibling, so sibling differentiation is partial rather than complete.

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?

It clearly documents two usage modes: calling with no arguments to list available properties and values, and calling with property/value to filter, backed by a concrete example. This gives an agent a clear context for invocation, but it offers no explicit when-not guidance or a rule for choosing this tool over 'buscar'.

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