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

Annotations already cover safety (readOnly, idempotent, non-destructive, open-world), so the description's real contribution is the cost disclosure (0.005 USDC per call via x402, with accepted chains), which annotations cannot express. It also clarifies that prices are each market's own HIP-3 oracle/mark. It does not state rate limits or pagination/response-size behavior for the whole-list mode.

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-loads the decision trigger, then the return payload, then the with/without symbol branch, then the pricing caveat. Every sentence carries distinct information; there is no repetition of the schema or annotations.

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?

With a rich output schema present, the description correctly avoids re-explaining return values and instead covers the decision context, the optional-parameter branches, and the non-obvious per-call cost/chain setup. Nothing needed to invoke it correctly is missing given the annotations and schema.

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 100%, so baseline is 3; the description adds value by showing two concrete accepted forms with examples (plain ticker TSLA/GOLD/EUR vs. dex-qualified xyz:TSLA) and explaining that dex-qualified markets exist, which the schema only implies. It stops short of stating matching/case rules explicitly.

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 (returns) and resource (Hyperliquid HIP-3 perp markets) with a precise scope, and enumerates the exact fields returned (oracle/mark price, premium, funding, OI, 24h change, dex). It is distinguishable from siblings like get_perp, get_equity_24h, and get_tradfi_radar because it names HIP-3 and the 24/7 off-hours use case.

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?

Opens with an explicit when-to-use condition ('when an agent needs a 24/7 price ... outside market hours') and specifies the when-to-use-symbol vs. omit-symbol branch, mapping each to a distinct output (every live market for it vs. the whole list). That is explicit conditional routing rather than implied usage.

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