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

With no annotations, the description carries the full burden. It does disclose extra behavior (computing trend stats) and lists available intervals, but it omits any caveats: error handling for unlisted coins, default values for parameters, or how the response is structured. It's read-only, so the lack of side-effect disclosure is minor, but an agent might be surprised by the computed stats or the exact output format.

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?

The description is two sentences, with the core function and value proposition front-loaded, followed by a focused usage note. Every phrase contributes: the data source, the computed stats, the interval options, and the intended use cases. No filler or redundancy.

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?

There is no output schema, so the description must explain what the tool returns. It lists the computed statistics (first/last close, percent change, high, low, average volume, direction) but does not describe the raw OHLCV candle fields, the response envelope, or how parameters like 'hours' and 'limit' interact to control the data volume. An agent might be able to call it, but without clarity on required parameters (all optional in schema) and output shape, it could misconfigure the request.

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 the baseline is 3. The description adds meaningful value for the interval parameter by enumerating allowed values ('1m, 5m, 15m, 1h, 4h, 1d'), and it implies 'coin' is the core input. However, it does not clarify the semantics of 'hours', 'limit', or 'symbol' beyond the schema's terse descriptions, leaving ambiguity about lookback vs. candle count and whether 'symbol' is an alias for 'coin'.

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 ('Hyperliquid perpetual OHLCV candles'), a precise resource ('any listed coin'), and the unique value-add ('trend statistics computed for you'). It clearly distinguishes itself from sibling tools like x402-hyperliquid-book or x402-hyperliquid-mids, which serve different data needs.

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 explicitly identifies when to use it: 'for momentum, breakout and mean-reversion checks on perps.' While it doesn't name alternative tools or exclusion criteria, the use cases are concrete and help an agent decide if this is the right tool. The guidance is adequate but not exhaustive.

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