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

Annotations already declare readOnly/idempotent/openWorld, so the safety profile is covered. The description adds genuinely non-redundant context: per-call pricing ($0.002/call or Carry key) and a universe restriction to the top 40 traded perps, both of which affect whether an agent should call it at all.

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 compact sentences: payload first, usage second. Only minor waste is the third clause which largely restates the opening resource description.

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 simple two-parameter read tool with no output schema, the description covers what the data is and its cost. It omits the shape of the return (hourly series?), valid coin identifiers, and the default/limit for `hours`, leaving real gaps for correct invocation.

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%, so the description must carry the load, and it explains neither parameter. It never says what format `coin` takes (Hyperliquid perp ticker?) nor what `hours` means, despite the schema capping it at 2160 (90 days) — a constraint an agent would want surfaced.

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 the specific resource with precise granularity and units: hourly order-book depth in USD at 5/10/20/50 bps per side plus spread. That clearly separates it from the funding-oriented carry_* siblings, though it never names an alternative tool to contrast with.

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?

The closing sentence 'Use for order-book depth history of a Hyperliquid perp' gives an implied use case, and the '40 most traded perps' clause sets a coverage boundary. There is no guidance on when to prefer a sibling (e.g. coin_snapshot or carry_history) or when this tool is the wrong choice.

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