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

The description includes a destructive action (delete_address: 'remove endereço'), but annotations declare destructiveHint=false. This is a direct contradiction. The description also fails to disclose other behavioral traits like authentication requirements or irreversible consequences beyond the annotation conflict.

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 moderately concise, listing actions in a clear bullet-like structure. The '[Flattened action: delete_address]' note helps. Some repetition of 'requer customer_id; data' could be streamlined, but overall it's efficient.

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 of multiple actions and no output schema, the description provides necessary action breakdowns and parameter roles. However, it lacks explanation of the 'data' parameter format, return values, error handling, and does not fully compensate for missing schema docs. The bulk support note adds some value.

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?

With 0% schema coverage, the description partially explains parameters: customer_id and address_id are linked to address actions, and data is mentioned for create/update. However, 'data' and 'account' remain unexplained, and the description does not specify the format or required fields within 'data'. The bulk parameters (customer_ids, address_ids) are mentioned but not detailed.

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 lists five actions (create, update, create_address, update_address, delete_address) and specifies required fields. The tool name includes 'delete_address', but the description clarifies it handles multiple customer and address write operations, distinguishing it from siblings like pagarme_customers_write_create which likely handles only create.

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 states required parameters for address actions (customer_id, address_id) and mentions bulk support, but it does not guide the agent on when to use this combined tool versus the more specific sibling tools (e.g., pagarme_customers_write_create, pagarme_customers_write_update, pagarme_customers_write_delete_address). No explicit when-to-use or when-not-to-use advice.

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