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

With no annotations supplied, the description carries the whole burden, and it discloses the important behavior that pending trading fees are collected before the transfer, that the destination cannot be redirected, and that a human/owner key signature is required over the payload. It does not cover failure modes such as insufficient balance or what happens to an unsigned first-call payload.

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?

Content is front-loaded with the destination guarantee, then the fee behavior, then the call sequence, then the fallback. The density is high but nearly every clause is operational; a light reordering into clearer steps would improve it without shortening 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 an unannotated mutation tool with no output schema, the description supplies the return shape of the first call, the signing requirement, and the degraded-path endpoint, which is most of what an agent needs. Missing pieces are error handling and any statement about whether a partial multi-rail signing is acceptable.

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?

The schema documents amount_usd and owner_signatures but leaves time undocumented; the description compensates by explaining that time belongs to the second call alongside owner_signatures keyed by rail. It also clarifies that amount_usd is exactly what gets signed, reinforcing the schema's note about 2-decimal precision.

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 states a specific verb and resource with explicit scope: 'Move USDC from your trading wallet back to your agent wallet, inside Hyperliquid,' and pins down that the destination is always the caller's own agent wallet. It also distinguishes itself from the outbound case by noting that leaving Hyperliquid is done via withdrawal from the agent wallet rather than this tool.

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 two-call protocol is spelled out: first call to obtain payload_b64 per rail plus the verify list, then a second call with time and owner_signatures. It also gives an explicit fallback for the no-API-key case (a terminated account) via a direct POST endpoint, and rules out using this tool to exit Hyperliquid. It stops short of naming a concrete sibling tool for the exit path.

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