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

With no annotations, the description does disclose two important behaviors: the order is reduce-only (so it cannot flip or increase exposure) and the action is two-step, requiring confirm_proposal on the returned id. It omits risk-relevant behavior an agent needs for a trading mutation — order type/price handling, permissions or allowance checks, and what happens if size exceeds the position.

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 short sentences, front-loaded with the action and its constraint, then the parameter hint, then the return contract. No filler; only minor compaction (merging the size note into the first sentence) would improve it.

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 mutation tool with no annotations and no output schema, the description covers the core flow (propose → confirm), the reduce-only guarantee, and the size default, which is the essential minimum. It is still thin on symbol format, walletId expectations, and failure/precondition behavior in an execution path where mistakes are costly.

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 only 33%: symbol and walletId are bare strings with no description anywhere. The description's one parameter statement ('Omit size to close the whole position') merely restates the schema's own size description, so it does not compensate for the undocumented symbol/walletId semantics.

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 (propose closing) plus resource (Hyperliquid perp position) with a scope qualifier (reduce-only), which cleanly separates it from propose_hyperliquid_perp_open and propose_hyperliquid_perp_modify without needing to name them.

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?

'Omit size to close the whole position' gives real usage guidance for the partial-vs-full case, and 'Returns a proposalId for confirm_proposal' implies the follow-up step. However, it never says when to prefer this over propose_hyperliquid_perp_modify or cancel_hyperliquid_orders, nor any preconditions (position must exist, allowance required).

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