sugerir_correcoes

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

With no annotations provided, the description carries the full burden — and it delivers. It discloses that the original text is never rewritten ('Não reescreve o texto original'), specifies the exact annotation format (<<ERRO: ...>> / <<AVISO: ...>>), guarantees each problem appears once ('uma única vez'), defines placement rules including the special-case block for header/missing-section issues, and clarifies that the doctor decides what to change. This is rich, non-obvious behavioral context an agent needs to invoke the tool correctly and interpret its output.

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 purpose is front-loaded in the first sentence, followed by dense behavioral details and a clean Args section. Every sentence earns its place, though the middle passage is information-dense and could be slightly better organized.

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?

An output schema is present, so return-value documentation is handled externally, and the single parameter is fully explained in the description. The behavioral contract (format, placement, deduplication, non-rewriting guarantee) is well covered; the only notable gap is explicit routing guidance against the sibling tool.

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 parameter meaning. The Args section explains 'texto_nota' as 'a nota completa a ser anotada', conveying that the input must be the full note and that it is the object being annotated — meaning the schema's bare title 'Texto Nota' does not provide. It stops short of format constraints (e.g., whether it must be a SOAP note), which is a minor gap.

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 opens with a specific verb and resource: 'Devolve a nota com anotações inline do que precisa ser ajustado' — returns the note with inline annotations of what needs adjustment. It also differentiates itself from its sibling validar_nota_soap by stating that each problem from that validation becomes an annotation line, making the boundary between the two tools clear.

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 reference to 'cada problema de validar_nota_soap' implies this tool consumes validation problems and renders them as annotations, giving the agent context about when it is relevant. However, it never explicitly states when to choose this tool over validar_nota_soap or when not to use it, leaving the routing decision to inference.

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