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

Beyond readOnlyHint/openWorldHint, the description discloses row granularity (exchange pair, not merged book), data provenance and refresh cadence ('CoinGecko's, updated on its own schedule'), and a per-call cost model ($0.002 USDC via x402 on Base/Solana/Arc, failed calls not charged). Cost and billing-failure semantics are exactly the behavioral context annotations cannot express.

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, return fields, and row semantics are front-loaded before the sibling routing and pricing notes, so the most important information lands first. The cost/payment sentence is dense but justified; the sibling clauses are chopped fragments that read awkwardly and could be tightened.

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 an output schema present, the description need not restate return values, and it still covers coverage scope, freshness, and pricing — the things the schema cannot convey. The only gaps are the garbled alternative-tool clauses and the absence of any note on error behavior beyond 'failed calls are not charged.'

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 100% and the single 'coin' parameter is already fully documented (coin id or ticker, ticker matched to the largest coin with that symbol). The description adds no additional syntax or format guidance for the parameter, 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?

The description opens with a specific verb+resource: per-exchange market depth for one coin, and enumerates exactly what is returned (USD cost to move price ±2%, 24h volume, last price, bid-ask spread, top 15 pairs). It explicitly states 'Each row is one exchange pair, not a merged order book,' which disambiguates the result shape from aggregate depth tools.

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 routes the agent away from this tool with concrete conditions: use crypto_hyperliquid_perps_depth for Hyperliquid L1 perpetual snapshots and crypto_binance_orderbook_depth for a single-pair Binance spot book. What's missing is an explicit statement of when this tool is the right choice versus those alternatives (e.g., cross-exchange CoinGecko coverage); the sibling clauses are also truncated ('best;', 'best bid.'), which weakens the routing signal.

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