propor_criar_cliente

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

The annotations declare readOnlyHint=false and destructiveHint=false, so the safety profile is already partly structured; the description usefully adds that nothing is persisted here, that internal duplicate search can refuse the proposal, that similar names return candidate lists, and that records cannot be deleted via this path. What it does not disclose is whether the pending proposal itself is stored or only returned as text, nor what the returned text contains — a meaningful gap given there is no output schema.

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?

Content is front-loaded and dense: the negated verb, the follow-up tool, the search rules, and the deletion caveat each appear once. The all-caps emphasis and telegraphic clauses slightly hurt readability, but no sentence is redundant.

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 6-parameter, two-step proposal tool with no output schema, the description covers the workflow, the refusal conditions, and the confirmation gate that an agent must not skip. Remaining gaps are the two undocumented parameters and the content of the text it returns to show the client.

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 only 33%, so the description must carry weight; it does explain the semantics of confirmo_que_e_novo (only true after asking the owner) and ties documento and nome to the duplicate/similarity refusal rules. However, email and perfil receive no explanation in either place, leaving a real coverage 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?

"Prepara o CADASTRO de um cliente ou fornecedor novo" names a specific resource and makes the non-obvious verb precise by immediately negating the naive reading ("NAO cadastra"). It also distinguishes itself from the sibling confirmar_acao, which it says must be called afterwards.

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 explicit when-to-use (new client or supplier), when-not (it does not persist anything), and the required follow-up tool (confirmar_acao). It also states the preconditions for proceeding — a clean document search and, for similar names, explicit owner confirmation plus confirmo_que_e_novo=true.

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