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

Annotations already cover read-only, open-world, idempotent, and non-destructive traits, so the bar is lower. The description still adds real value: free tier of 100 calls/day, then 0.002 USDC per call on Sui mainnet with prepaid batches, the payment-required response flow, and a data-quality caveat ('may be delayed or wrong'). This goes well beyond the annotations.

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?

It is correctly front-loaded, leading with the returned signal before caveats and pricing. However, two adjacent sentences repeat the same disclaimer ('Information only, not a trading instruction' / 'Education/information only; not financial advice'), and the payment paragraph is long relative to its value. Some pruning is warranted.

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 no output schema, the description must carry return-value semantics, and it does: it enumerates the ranges, volatility, regime buckets with numeric thresholds, and the rung count, plus the payment response handling. It is nearly complete, missing only finer response-shape details.

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 schema already documents pool, payment_tx, and payment_token fully, making 3 the baseline. The description only gestures at payment_token indirectly ('the payment-required response gives an exact amount and a payment_token') and adds no syntax or format detail beyond the schema. Adequate but not additive.

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 derived resource: 1h/4h/24h high-low range, realized volatility, a regime classification with thresholds, and a suggested ladder rung count. This clearly distinguishes it by content from raw-data siblings like get_ohlcv or get_volume. It stops short of naming a sibling alternative, so it lands at 4 rather than 5.

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?

There is no guidance on when to use this versus get_ohlcv, get_volume, or get_mid_price, nor any exclusions. The only contextual rules are the free-tier/payment constraints, which govern cost rather than tool selection. An agent gets no help choosing among the signal-oriented siblings.

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