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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, not open-world), and the description adds real behavior: results are cost-adjusted at the caller's size (fees + order-book slippage), capacity-limited via max size, and validated by a settled 7-day replay. That goes meaningfully past what the annotations declare.

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?

A single dense sentence with the ranking concept and cost model front-loaded and zero filler. It is slightly run-on with a long parenthetical list, but every clause contributes a distinct output or constraint.

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?

No output schema exists, so the description carries the return-value burden and does so by enumerating the ranked fields (net, max size, breakeven, replay, tier, reasons). With 6 optional params and full annotation coverage, remaining gaps (cost of the computation, ordering ties) are minor.

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 83%, so the schema baseline is 3; the description still adds linkage the schema lacks by tying 'at your size' to the notional semantics and by explaining that the replay is settled over 7 days (matching holding_hours=168). Tier naming ('actionable / watch') also implicitly clarifies what actionable_only controls.

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 (ranked funding-rate arbitrage pairs, long one market / short another) and enumerates the computed outputs: net after taker fees and slippage, max size, breakeven, 7-day replay, tier, reasons. An agent can distinguish this from funding_rates or pair_breakdown by the ranking/fee-adjusted framing, though no sibling is named explicitly.

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?

The description never says when to reach for this versus alternatives like basis_trades, pair_breakdown, or funding_rates, nor does it state prerequisites or when results are meaningless. Usage must be inferred from the output list and the 'actionable / watch' tier vocabulary.

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