Reprocessar falhas

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

Description adds behavioral context beyond annotations: requires confirm=true, processes in blocks, and suggests pre-correction for rejected notes. Annotations already indicate mutation (readOnlyHint=false) and idempotency (idempotentHint=true), which aligns. Minor gap: not stating what happens if confirmar is false.

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?

Two sentences, front-loaded with main purpose, uses emphasis appropriately. Every sentence adds value with no waste.

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?

Given 3 parameters and no output schema, the description covers basic operation but leaves gaps: não explica o parâmetro 'tamanhoBloco' nem o comportamento de 'processa em blocos' em detalhes. Could be more explicit about return or side effects.

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 coverage is 33% (only confirmar has a description). The description adds that confirmar must be true and hints at block processing for tamanhoBloco, but does not clarify competencia or tamanhoBloco defaults/values. Marginal improvement over 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?

The description clearly states it reissues only notes with rejected/error status from the period, reusing loaded data. This is specific and differentiates from siblings like emitir_nfse (emission) or carregar_csv (loading).

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 description explicitly says when to use: only for notes with rejected/error status, and advises to correct the cause for rejected notes before calling. It does not explicitly name alternatives but implies not to use for other statuses.

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