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

Annotations already declare readOnly, idempotent, open-world, so the safety profile is covered. The description adds genuinely non-structured context: a per-call price of 0.010 USDC (included in subscriptions), the verdict vocabulary (ok/caution/avoid/unknown), and explicitly how missing data is surfaced as 'unknown'. It does not describe latency, rate limits, or pagination.

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 data coverage and ends with the return/verdict semantics and pricing. Three sentences with little waste, though the opening sentence is a dense run-on list of venues and metrics that could be split.

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 burden and does reasonably well: verdict values, reasons, per-venue costs, and cheapest venue are all stated. Minor gaps remain — the exact shape of the per-venue cost breakdown and how size_usd defaults interact with the output are unstated.

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, size_usd (default 10000, max 5,000,000, must be positive) is not. The description references 'an order of the given size' and 'all-in cost on each venue', which ties size_usd to the cost calculation, but it does not explain the default, the cap, or the USD units beyond what the param name implies.

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 the exact data sets (funding, open interest, liquidations, order book depth), the venues covered (Binance, Bybit, OKX, Hyperliquid, Drift, plus Jupiter), and the composite output (all-in execution cost with cheapest venue). This is far more specific than any sibling and an agent can distinguish it from pool_health or swap_preflight immediately.

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 — this is the pre-trade market/venue comparison tool — but the description never states when to prefer it over siblings like swap_preflight or pool_health, nor any exclusions or prerequisites. No alternative is named, so the agent must infer routing.

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