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

Goes well beyond the annotations (destructiveHint, idempotentHint, openWorldHint) by disclosing outcome states (`no_change`, `unknown`), the retry hazard on unknown outcomes, and the untrusted-content safety rule for broker/hook/person data. This is exactly the behavioral context annotations cannot convey.

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?

Three tightly packed sentences: the operation and its partial variant come first, then failure semantics, then the safety warning. No filler, and the most decision-critical content is front-loaded.

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, it covers the states an agent must handle (partial vs full, no_change, unknown + recovery path). It omits what a successful response contains and any permission prerequisites, keeping it from a 5.

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%, so the schema already explains volume, client_request_id, reason, account_id and position_id. The description only echoes that volume is in lots and optional-inferred full close, adding no meaning beyond the schema. Baseline 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') and qualifies scope ('fully, or partly when volume (lots) is given'). It distinguishes itself from modify_position/cancel_order implicitly by naming position closure, but never names a sibling explicitly, so it stops short of 5.

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?

Gives concrete operational guidance: closing an already-closed position returns `no_change`, and on an `unknown` outcome the agent must not retry with a new client_request_id and should call get_trade_status/get_positions/get_orders first. It does not state when to prefer close_position over modify_position or cancel_order, which keeps it below 5.

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