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

Annotations cover read-safety, but the description adds genuinely non-structured context: payment is required via x402 (USDC on Base) passed in _meta["x402/payment"], the price is $0.003 per successful call, bad input is free, and calls touching fewer than two venues are not charged. This is exactly the auth/payment/cost surface an agent cannot infer from 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?

The core capability and venue list are front-loaded and nearly every clause carries information. The opening sentence is dense and run-on, and the 'L2 orderbook liquidity for BTC, ETH, SOL and more' clause partially repeats the coin parameter example, keeping it just short of a 5.

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 carries the return-value burden and does so thoroughly by enumerating every returned metric. Combined with billing and payment details, an agent has everything needed to call it correctly and understand the cost before invoking.

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 coin/levels/size_usd are already fully documented, including example symbols. The description mentions 'estimated slippage for your order size' and 'top N levels' but adds no format or default detail beyond the schema, so the baseline 3 applies.

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+resource ('Order book depth of one coin's perpetual') and enumerates eight named venues plus the exact metrics returned (best bid/ask, spread bps, depth in USD within 0.1/0.5/1/2% of mid, imbalance, slippage, walls). None of the siblings (funding, OI, liquidations, basis) overlap, so an agent can route to it unambiguously.

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?

Usage is implied by the returned metrics: an agent wanting spread/depth/slippage for a single coin on multiple perp venues will infer this is the tool. However, no sibling is named as an alternative and no explicit when-not guidance is given; billing rules ('bad input is free', 'under 2 venues not charged') describe cost, not selection criteria.

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