PerpCheck

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

With readOnlyHint already declaring safety, the description still adds substantial non-obvious context: free-tier quota (30/day, 10/min), that invalid input is not counted, and the exact failure mode (error containing an x402 pay URL, with $0.01/full and $0.003/lite tiers). That is genuinely useful for deciding whether to call it. It stops short of saying how far the 10/min limit is enforced or what happens to a partially degraded check, so it is not 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?

Front-loaded well: verdict and return shape come before pricing and disclaimers, which is the right order for an agent skimming. It loses a point for redundancy — the 'read-only, never places/signs, needs no keys' claim appears twice, once mid-paragraph and again as a closing sentence, and the 'not financial advice' disclaimer occupies space an agent does not need.

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 8-parameter tool with no output schema, the description enumerates the return surface thoroughly: verdict tiers, issues[] with fix values, warnings[], rules, isolated liquidation estimate and distance, taker impact, funding carry, market facts, confidence, and sources_failed. Combined with coverage of quota, pricing, and failure behavior, an agent has everything needed to call it and interpret the result.

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 already 100%, so 3 is the floor. The description adds value by stating that coin/side/size should be supplied 'as you would send it' (so decimals and tick format are validated as-typed) and by restating the size-or-notional alternative, which frames the two mutually exclusive sizing paths in the prose rather than only in the property docs.

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?

Names a specific verb (checks) and resource (Hyperliquid perp order) with a clear temporal scope: before submission. The addition of 'would the exchange reject it, and what does it cost and risk' precisely frames what the check returns, so an agent knows the tool's output domain 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?

Explicitly states when to use it ('BEFORE your agent sends it') and draws the boundary against the actual order path ('never places, signs or holds orders and needs no keys'). It also gives input-mode guidance inline (omit price = market order; size in coins vs notional in USD), removing the main ambiguity an agent would hit at call time.

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