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

With no annotations supplied, the description carries the full burden and does so: both legs pass through policy, grant, loss cap and audit checks; required key permissions are named; nothing is placed if co-signer approval is needed on either leg. It also discloses atomic failure semantics (spot bought then short fails → automatic sell-back with unwound=true; if that fails, hedged=false and unwound=false), the absence of a size cap beyond policy, and the margin-call risk of leaving too little spare cash.

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 mechanism, then guardrails, then failure handling, then exit instructions — a logical order with no filler sentences. It is dense and slightly crammed into a few long compound sentences, which costs a point on readability but not on usefulness.

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?

This is a complex, multi-leg, atomic mutation with no output schema, and the description still covers preconditions, permission requirements, failure and partial-failure states with their result fields, sizing guidance, and how to unwind. An agent has everything needed to decide whether to call it, to dry-run it first, and to handle every documented outcome.

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 80%, so most parameters are already documented, but the description still adds value: dryRun is reframed as a planning tool that shows sizes and cash needed before anything is placed, and sizeUsd is clarified as the dollar size of EACH leg rather than a total. walletId and perpLeverage are left entirely to the schema, which limits it to a 4.

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 opening clause states a specific verb and composite resource: 'Funding carry in one call: buy the coin on spot, then short the same size on its perp.' It immediately explains the economic mechanism (price moves cancel, short earns funding), which distinguishes this atomic two-leg tool from the sibling single-leg proposers like propose_hyperliquid_spot_order and propose_hyperliquid_perp_open that 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?

Explicit when-to-use (funding is positive), when-not (funding not positive, spot/perp prices more than 2% apart, account already runs a strategy, either leg would need co-signer approval), and the recommended preflight (dryRun=true to see sizes and cash needed). It also names the exit path — unwind with propose_hyperliquid_perp_close plus propose_hyperliquid_spot_order side=sell — and the manual recovery call if the automatic unwind fails.

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