prepare_perp_order

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

The description adds real context beyond the readOnly/idempotent annotations: it declares zero-custody behavior, enumerates what is returned (action, typed data, nonce, expiry, intent hash), and explicitly states the server never signs or submits — consistent with readOnlyHint=true and destructiveHint=false. The tier gate and authority endpoint are also disclosed. Missing are failure/error modes and any rate-limit or retry behavior, so it falls short of a 5.

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?

Two dense sentences front-load the action and the signing boundary, and every clause carries information about behavior or gating. The bracketed capability/tier/API header is metadata clutter that consumes the opening position without helping selection.

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 17-parameter order-construction tool with no output schema and zero schema coverage, the description is under-specified: it sketches output contents but leaves parameter usage, mode selection, and the grant/session requirements for gated execution unexplained. An agent would have to guess at several fields before it could call this reliably.

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% across 17 parameters, so the description carries the full explanatory burden — yet it explains no parameter at all. Fields with non-obvious semantics and constrained enums, such as executionMode (USER_SIGNED vs BOUNDED_AUTONOMOUS), reduceOnly, grantId, sessionToken, continuationId, and executionTrialId, are left for the agent to infer.

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 ('Prepare an exact zero-custody Hyperliquid order for local EIP-712 signing') and clarifies the boundary against the execute path by saying it 'never signs or submits.' It stops short of naming the sibling it must precede (execute_perp_order) or contrasting with simulate/analyze tools, so differentiation is implied rather than explicit.

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?

It gives a concrete precondition split: 'New-risk preparation requires a fresh execution-ready analysis; reduce-only preparation remains authority-bound at execution.' That tells the agent when this call will be gated and on what basis. It does not, however, state where this fits in the sequence relative to analyze_futures_strategy, calculate_position_size, or execute_perp_order.

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