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

Annotations declare a write operation (readOnlyHint=false, idempotentHint=false), and the description adds the crucial behavioral fact that the first call is a pure quote with no side effects, which is not inferable from the annotations. It does not cover permissions, error behavior, or whether retries duplicate orders, so it stops short of a 5.

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?

Three short sentences: what it does and returns, the two-step gate, and the routing to the alternative. Front-loaded and every sentence carries load.

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 an 11-parameter, nested, non-idempotent write tool with no output schema, the description covers the creation flow, the safe quoting path, and the return payload. It leaves gaps on failure/duplicate-submission behavior, but the agent has enough to invoke it correctly in the normal path.

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 27%, so many nested parameters (comprador, endereco, frete, verso, quantidade_por_tamanho) rely on the schema alone. The description does add real meaning for the pivotal confirmo_total parameter beyond its schema note (it must equal the quoted total and requires buyer approval), which keeps it at 3 rather than lower.

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 ('Cria o pedido') plus what it returns (Pix copia e cola and Mercado Pago card link). It also explicitly separates itself from the sibling montar_link_de_compra by noting that this tool uses text art, not image art.

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 an explicit two-stage protocol: without confirmo_total it only calculates the total and creates nothing; with confirmo_total matching the total and the buyer's approval, it creates the order. It also names the alternative (montar_link_de_compra) and the condition that selects it.

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