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

Goes well beyond readOnlyHint=false and destructiveHint=true by disclosing that real funds move, that user confirmation is needed, that execution happens directly under the apikey identity, and that an authorization gate can block the call. This is exactly the risk context an agent needs before invoking a destructive trading tool.

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?

Dense, front-loaded single paragraph that leads with the write-operation and real-funds warning before parameters and auth. The trailing '(cost: free)' and apikey note are slightly tacked-on but still add value.

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 an 11-parameter destructive order tool with no output schema, it covers the critical items: credential source, notional amount, order type and price dependency, and the authorization gate. Minor gaps remain on idempotencyKey, slPrice/tpPrice, and leverage semantics, though those are documented in the schema.

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 the baseline is 3, but the description adds real meaning: credentialId must come from platform_credentials, amount is a USDT notional (not base-asset quantity), and orderType accepts market|limit with price required for limit orders — an enum-like constraint absent from the schema itself.

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 ('真实下单', a real-money write operation) and scopes it to position/execution scenarios. It is clearly different from read-only siblings like platform_positions or platform_trade_history, though it does not explicitly contrast itself with platform_close_position or platform_dex_swap.

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 a concrete prerequisite: account-level '「AI 实盘授权」' must be enabled or the call is rejected, and notes confirmation is required. It does not say when to prefer this over platform_dex_swap or platform_cancel_order, so the routing guidance stops short of explicit alternatives.

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