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

Annotations show readOnlyHint=false, indicating a write tool. The description adds context: it requires secret key (sk_), lists mutating actions, and mentions bulk execution. It discloses behavioral traits beyond annotations, though no rate limits or error behavior is covered.

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 structured as a list of actions with bullet points, making it easy to parse. It is somewhat lengthy due to enumerating actions but remains organized and front-loaded with the main purpose.

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?

Given the complexity (multiple actions, no output schema, limited annotations), the description covers action requirements and bulk support. However, it lacks return value details, error behavior, and explanation of 'Flattened action: update'. It meets minimum completeness but has gaps.

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?

The input schema has 0% description coverage, but the description provides detailed semantics for each action, mapping parameters to required fields (e.g., data: { amount } for create_withdrawal). This fully compensates for the lack of schema descriptions.

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 it handles multiple write operations on recipients (create, update, update_bank_account, etc.) and distinguishes from sibling tools like pagarme_recipients_get or pagarme_recipients_write_create. It's specific about the scope ('Criar/operar recebedores'), though the verb 'operar' is generic.

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 enumerates each action with its required parameters (e.g., update requires recipient_id and data; create_withdrawal requires recipient_id and data: { amount }). It also mentions bulk support via recipient_ids. However, it does not explicitly exclude cases or compare to alternatives like pagarme_recipients_write_create.

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