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

Annotations only say it is a non-read-only, non-destructive, non-idempotent open-world call; the description adds the crucial fact that this is a prepare step that must be completed by a separate signing/submission call, and that the signing party differs by source account (owner vs agent wallet). It also discloses fee behavior: no fee of its own, with Circle/Polymarket bridge fees surfaced in the summary. This is exactly the kind of multi-step, auth-dependent behavior annotations cannot convey.

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?

Front-loaded with the core action and the three endpoints, and every sentence carries operational content. It is dense with nested parentheticals (wallet glosses, fee caveat, signing instructions), which is efficient but slightly hard to parse on a first read.

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-style tool with no output schema, the description covers the important missing pieces: the two-step submit flow, which key signs which branch, and fee handling. It leaves out failure conditions (insufficient balance, minimum transfer size) and what the "summary" object contains, which an agent may still need before calling.

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?

With 100% schema description coverage, the enum values and amount_usd are already documented, so the baseline is 3. The description reinforces what perps/predictions/earn_usdc actually are and ties the earn_usdc source to an extra owner_public_key, but it says nothing about the `all` flag's interaction with amount_usd or any minimum/threshold on amounts.

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 ("Move money between YOUR accounts") and enumerates the exact endpoints: perps, predictions, earn_usdc, each with a short gloss (trading wallet on Hyperliquid, Polymarket deposit wallet, trading wallet's USDC on Base). An agent can distinguish this from transfer_spot_perps, earn_usdc_deposit, or send_trading_funds_home without opening the schema.

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 conditional next-step routing: moves from perps or earn_usdc return an operation for submit_operation, while moves from predictions return a batch for submit_predictions_batch. It also names the owner_public_key requirement for owner-signed Base transactions. It does not explicitly exclude the overlapping funding siblings (earn_usdc_deposit/withdraw, transfer_spot_perps, send_trading_funds_home), so the choice among them is left partly to inference.

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