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

Annotations already indicate readOnlyHint=true and idempotentHint=true. The description adds that filtering is done via the 'data' parameter with typical list filters (count, page, status), and notes that field differences across versions come raw in the payload. However, the mention of 'bulk support: accepts transaction_ids' is questionable for a list_customers operation and may mislead. Overall, adds moderate behavioral context beyond annotations.

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 overly verbose, containing a full list of actions that belong to multiple other tools. The flattened action notation helps, but the bulk of the text is not focused on the tool's specific function. This verbosity reduces clarity and makes it harder for an agent to quickly parse the essential information.

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, and the description does not explain the return value format or structure. While it mentions field differences in payload, it omits what fields to expect. For a legacy API with multiple versions, more detail on response shape would be valuable. The description also fails to clarify how the 'transaction_id' and 'transaction_ids' parameters relate to listing customers.

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 must explain parameters. It only partially explains 'data' (filters as JSON) and implicitly 'account' (string for account identifier). The parameters 'transaction_id' and 'transaction_ids' are not explained and seem irrelevant to listing customers. This leaves significant ambiguity for an AI agent.

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 is for the legacy Pagar.me API (V1-V4) and the flattened action specifies 'list_customers'. However, it includes a list of other actions (list_transactions, get_transaction, etc.) that are not the focus of this tool, causing some confusion. The tool name and context signals indicate a specific listing purpose, and the distinction from modern API (V5) is implicit but present.

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 provides a condition: use when the connection uses an ak_ key (accounts not migrated to V5). This helps decide when to use this legacy tool instead of modern alternatives. However, it does not explicitly name sibling tools like pagarme_customers_list for comparison, though the context is sufficiently clear.

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