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

Adds substantial context beyond the sparse annotations: api:trade scope with 403 behavior, the user's separate API-trading opt-in, agent-deposit-wallet-only constraint, expiry of unconfirmed proposals, and the exact return payload (proposal_id, expiry, preview fields, confirm_echo). None of this is in the structured fields.

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?

Long but dense, and the critical non-execution guarantee is front-loaded in the second sentence. Every clause carries distinct operational information (auth, wallet, returns, expiry), though it could be tightened slightly.

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?

With no output schema and thin annotations, the description carries the full burden and discharges it: it documents the return shape, the auth/scopes, wallet restrictions, the close semantics, and the confirm handoff. An agent has everything needed to call and route this 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 description coverage is only 25% (just notional_usd), so the description must compensate. It clarifies side=close as a reduce-only close and ties confirm_echo to asset/side/size_usd, but leaves symbol, leverage, and the long/short distinction unexplained. Partial compensation, not full.

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+resource ('Stage a guardrailed trade preview') and immediately disambiguates from actual execution with 'This does NOT place anything', separating it from confirm_trade. An agent can tell from this alone that it produces a proposal, not an order.

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 clear context: preview must be presented to the human, the proposal expires if not confirmed, and confirming requires echoing the confirm_echo. It implies the confirm sibling rather than naming it explicitly, so it stops just short of a named alternative.

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