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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, and the description is consistent with them while adding real value: it enumerates the returned quantities in the absence of an output schema and explicitly guarantees no order is placed or signed. It does not describe error behavior (e.g. invalid entry/invalidation geometry) or what makes reward-to-risk 'optional'.

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?

A single dense sentence, front-loaded with the return values and closed with the key safety guarantee; nothing is padded. Minor cost: 'optional gross reward to risk' and 'evidence packet' are compressed to the point of ambiguity.

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 six-parameter calculation tool with no output schema, the description does state what comes back and confirms non-execution, which covers the essentials. It falls short on the actual sizing logic (how risk_usd and the entry/invalidation distance combine), the optional relation between target and reward-to-risk, and the unexplained 'evidence packet'.

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 0%, so the description carries the full burden, yet it only gestures at 'user supplied levels' and never explains risk_usd (the basis for position sizing), symbol, direction, or how invalidation defines the risk distance versus target. It also references an 'evidence packet' input that does not exist among the six declared parameters, which actively muddies parameter understanding.

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?

The description names a specific computation and its outputs: position quantity, notional and gross reward-to-risk derived from user-supplied levels. It is clearly a sizing/calculation tool rather than an execution tool, which distinguishes it from the read-only siblings, though it never names an alternative or explains how the sibling get_decision_packet relates to the 'evidence packet' it references.

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 clause 'without placing or signing an order' implicitly tells the agent when this tool applies (pre-trade planning, no execution), which is useful context. However there is no explicit when-to-use/when-not guidance, no statement of prerequisites (where the 'evidence packet' or levels come from), and no routing to a sibling for order placement.

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