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

Annotations declare destructiveHint=false, but the description describes cancellation (destructive), creating a contradiction. No additional behavioral traits (auth, rate limits, side effects) are disclosed beyond the action itself.

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 concise but front-loads general charge actions before specifying the flattening to cancel. It wastes no sentences, though the initial list could confuse if not read carefully.

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?

No output schema exists, and the description lacks details on return format, errors, or prerequisites. For a mutation tool with no schema descriptions, this is insufficient for complete understanding.

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%, so the description should compensate. It mentions charge_id and charge_ids but omits 'account' and includes 'amount_cents' which is only relevant for refund, potentially misleading. No parameter formatting or constraints are described.

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 clearly states the tool cancels charges ('cancela uma cobrança'), distinguishes from get and refund actions, and supports bulk via charge_ids. Sibling tools for get and refund further clarify its unique purpose.

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 description specifies that cancel applies to charges not yet captured ('ainda não capturada'), explicitly differentiating from refund (estorno) and indicating bulk support. This gives clear guidance on when to use this tool.

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