criar_pagina

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

With no annotations at all, the description carries the full behavioral burden and does reasonably well: it discloses the return payload ('Devolve id, link e avisos'), the ONMD content format, the rule that the title must go in the parameter and never in the body, and how retroactive dates work. It omits permission/auth requirements, duplicate-title behavior, and failure modes, so it is not fully complete.

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 statement is not front-loaded; the reader must wade through workflow text first. Worse, several sentences are about editing rather than creating ('Antes de editar, leia a página...', 'Depois de edição estrutural, releia'), which belongs to the editar tool and dilutes this definition. The remaining content is dense and earns its place.

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 5-parameter tool with a nested anexos object, no annotations, and no output schema, the description covers the essentials: what it creates, the content format, attachment mechanics, date handling, and what is returned. Missing are authorization expectations and error/duplicate behavior, but an agent could call it correctly with what is here.

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% for the top-level parameters, so the description must compensate and largely does: secao accepts an id or path, conteudo is ONMD, anexos is documented with an inline JSON example plus the citation syntax  / <anexo n=2/>, criado_em is AAAA-MM-DD, and titulo's placement is stated. Only minor format details (e.g. exact section path syntax) are left implicit.

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 contains a clear verb+resource statement: 'Cria página nova na seção (id ou caminho)', and it is obvious this is a creation tool rather than a mutation of existing content. However, the purpose sentence is buried after a paragraph of workflow instructions, and it never explicitly contrasts itself with close siblings like editar, inserir, or acrescentar, leaving the agent to infer the boundary.

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 opening paragraph gives process context ('Antes de escrever, leia a spec... não invente sintaxe', 'Faça a menor edição possível', 'Relate os avisos'), which is genuinely useful pre-write guidance. But it does not answer the key routing question for this tool family: when to create a new page versus edit/insert into an existing one via editar or inserir. Usage is implied rather than explicitly scoped.

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