get_closed_positions

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

No annotations are provided, so the description carries the full burden. It discloses the pagination behavior, the opaque nature of the cursor, and the requirement for API credentials. It does not explicitly state whether this is a safe read operation, but the verb 'get' implies read-only. The description adds value beyond the schema by explaining the pagination loop and the meaning of 'next_cursor'. Missing explicit mention of rate limits or potential errors, but acceptable given the simple read operation.

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, clear, and well-structured. It starts with the purpose, then explains the output format and pagination flow. Every sentence provides necessary information without redundancy. The structure is logical: what it returns, how to paginate, and a note on credentials. No fluff.

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 tool's complexity (pagination) and the absence of output schema, the description is complete. It explains the return format ('items' and 'next_cursor'), the pagination algorithm, and the semantics of each parameter. It even warns about not modifying cursors. The description covers all necessary aspects for an agent to use the tool 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 parameters are well-documented. The description adds extra semantics: 'limit' sets the size of ONE page, not a total, and 'cursor' should be passed verbatim, never constructed. This goes beyond the schema's basic description, providing operational context that helps correct usage. The clear explanation of cursor usage is particularly valuable.

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 action ('Get the authenticated account's closed positions') and specifies the content ('realized PnL per position'). It distinguishes itself from sibling tools like get_positions (likely open positions) by explicitly including 'closed'. The pagination details further clarify the tool's 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 provides explicit usage guidance on pagination: how to use the cursor, when to stop, and the meaning of 'limit' as per-page not total. It does not explicitly mention when to prefer this over alternatives, but the context ('closed positions') makes the use case clear. Slight deduction for not contrasting with other history-oriented tools like get_fills or get_order_history.

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