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

Annotations cover the safety profile (destructiveHint, idempotentHint, openWorldHint, readOnlyHint=false), but the description adds substantial context the annotations cannot: the payout_address irreversibility and trust-source constraint, the 24 h provider hold state machine (held → paid → delayed → paid), the R$ 6,000/day refusal ceiling, the image-rendering fallback, and the warning that a QR is a payment request rather than payment proof.

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 description is long, but the length is earned by the irreversibility and compliance stakes, and the critical warning (payout_address is irreversible) is front-loaded right after the charge mechanics. Some material such as the compliance warning and the output-display instructions could be trimmed, keeping it just short of top marks.

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?

There is no output schema, so the description carries the return-value burden and does so: it names qr_copypaste, amount_cents, expires_at, held/held_hours, hold_hours and cashin_id, and warns that paid alone does not confirm crypto delivery. The error taxonomy is also fully specified, leaving nothing an agent needs in order to call it correctly.

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 100%, so the schema already documents each parameter, which sets a baseline of 3. The description goes further by clarifying that amount_cents is an integer in cents rather than reais or a float, that external_id exists to make retries safe, and that payer_tax_number must be the real payer under Central Bank rule, and it stresses confirming the full payout address rather than a truncated form.

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 states a specific verb and resource (creates a PIX charge returning a QR code and copy-and-paste string) and the side effect that matters most (crypto delivered to payout_address on payment). It clearly differentiates itself from siblings by naming lunium_check_payer_limit and lunium_get_pix_charge as related steps.

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?

It gives explicit sequencing (call lunium_check_payer_limit first), a prohibition (do not create a new charge while a previous one for the same intent is pending or delayed), an idempotency instruction (send external_id so a retry does not create a second charge), and error-branch routing (acao=corrigir/esperar/repetir). These are concrete when/when-not conditions with named alternatives.

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