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

Annotations already establish readOnly/openWorld/idempotent, so the bar is lower; the description adds genuinely new context by disclosing the external venue coverage and the cost model (0.010 USDC per call, included in subscriptions), which is important pre-invocation information. It stops short of describing determinism of 'cheapest venue', latency, or failure modes when a venue is unreachable.

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?

Front-loaded with the returned data and scope, then a short pricing sentence; every clause carries information. The venue/data enumeration is long but not redundant, and there is no filler.

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 burden of describing returns and does so thoroughly (per-venue metrics, divergence, all-in cost, cheapest venue). It omits response shape, handling of unsupported tickers, and the meaning of the size default/maximum, which keeps it from a 5.

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 50%: symbol is documented ('Ticker such as SOL') but size_usd has no schema description, leaving its unit and semantics partly to the name. The description partly compensates by framing the tool around 'the all-in cost of an order of the given size on each venue', but never states that size_usd is a USD notional, so the baseline 3 is appropriate.

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 names concrete resources (funding, open interest, liquidations, order book depth, execution cost) and the exact scope (Binance, Bybit, OKX, Hyperliquid, Drift, plus Jupiter), so an agent knows this is a cross-venue perp market snapshot. It distinguishes itself from siblings like pool_health or swap_preflight by content, though it never references them by name.

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 data enumerated — you call this when you need cross-venue funding/OI/execution-cost comparison for a ticker at a given order size. There is no explicit when-to-use, when-not-to-use, or named alternative (e.g. swap_preflight for a single swap), so the agent must infer the routing itself.

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