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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered structurally. The description adds two useful facts beyond the annotations: closing can be partial, and an API key is required. It does not explain what happens on repeat calls or against an already-closed position, so it stays at a modest level.

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?

Two short, front-loaded sentences with no filler; the core action comes first and the prerequisite second. It is efficient, though the auth note is near-boilerplate across this tool family.

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?

For a destructive mutation with no output schema, the definition omits important operational context: where the id comes from (presumably paper_positions), what a partial close does to realized P&L, and error behavior. Annotations cover the safety hint, but an agent still lacks enough to call this confidently in edge cases.

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 only 50%: the required 'id' parameter carries no description anywhere, and the description never clarifies whether it refers to a position id, order id, or account id. The 'fully or partially' phrase loosely maps to 'pct', but the schema already documents that parameter's 1-100 range, so the description adds no compensating meaning for the undocumented half.

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?

States a specific verb and resource ('Close a simulated position') and adds the full/partial scope, which is the key distinction from a plain close. It does not explicitly name sibling tools (e.g. paper_open, paper_modify_order), but the action is unambiguous on its own.

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 prerequisite 'Requires an API key' is stated, which is real guidance. However, there is no when-to-use vs alternative framing — an agent gets no help distinguishing closing a position from paper_modify_order, paper_cancel_order, or paper_sltp on the same account.

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