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

Annotations cover only the generic safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false). The description adds behavior an agent cannot infer: all-or-nothing atomicity ("se faltar em um item, a nota inteira é recusada e nada é gravado"), the side effect that upCampo auto-registers a missing fornecedor, and the confirm-before-write workflow. These are exactly the traits annotations cannot express.

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-loads the core purpose, then layers mode requirements, the critical id_local_estoque constraint, and the write/confirm workflow – a logical order with no wasted sentences. Slightly dense, and a few clauses (fornecedor sourcing, produto_descricao) echo schema text, but nothing is padding.

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 13-parameter, nested-item write tool this is thorough: it covers both operating modes, required-field logic, dependency tools, the atomicity failure mode, the auto-cadastro side effect, and the confirmation workflow. An output schema exists, so return values need not be explained, and no gap remains that would cause a failed call.

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 the baseline is 3; the description still adds cross-parameter meaning beyond the schema – how tipo drives which of numero/descricao/fornecedor become required, that produto_descricao substitutes for id_produto when the product is unregistered, and that a single missing id_local_estoque rejects the whole note. That is genuine semantic value on top of an already complete 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 ("Registra uma entrada de material no estoque") and immediately splits the operation into its two distinct modes ("Entrada avulsa" vs "Entrada com nota fiscal"), so an agent knows exactly what this tool produces. The resource is unambiguous against all lancar_* siblings (abastecimento, chuva, OS), which cover entirely different domains.

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 mode-specific conditions (avulsa needs descrição, nota fiscal needs número and fornecedor) and routes the agent to dependency tools: fornecedor from consultar_estoque or an existing cadastro, id_safra from listar_safras, id_local_estoque from consultar_estoque visão "locais". It also instructs to summarize and confirm before calling. It stops short of explicitly naming an alternative entry tool to prefer under some condition, but the branching guidance is strong.

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