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. The description adds genuinely new behavior beyond that: paper mode executes immediately while live mode returns typed_data for signing, which is a critical two-step flow an agent must know before calling. It does not cover failure cases (e.g. no such position) or whether partial closes are reversible.

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 sentences with no wasted words; the operation and its sizing modes come first, followed by the mode-dependent outcome, which is exactly the right front-loading.

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 two-parameter destructive tool with no output schema, the description covers the essential unknowns: what it acts on, sizing, and the divergent paper vs live return path. It stops short of error/precondition behavior and confirmation expectations for an irreversible action.

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 100%, with both market and size_pct already documented including the omit-to-close-all default and the 1-100 range. The description's mention of 'fully or size_pct' merely restates the schema, so the baseline of 3 applies.

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 an open position) plus the two modes of operation (full vs size_pct). An agent can distinguish it from read tools like get_positions, though it does not explicitly name the nearest siblings such as cancel_order or protect_position.

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?

Invocation context is implied by 'open position' and the paper/live split, which tells the agent something about when execution differs. However, there is no explicit when-not guidance or routing against adjacent tools like cancel_order or protect_position, leaving the agent to infer.

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