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

Annotations only declare readOnlyHint and openWorldHint; the description adds real behavioral context: Monte Carlo on live Deribit implied vol, the free-preview limitation, and the x402 payment-requirements retry flow. This is valuable beyond the annotations, though the pricing/payment detail is repeated rather than refined.

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 sentence is well front-loaded, but the $0.02 USDC / x402 payment terms are restated three separate times, wasting space. Effective content is there, but the repetition costs it.

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?

For a single nested-object param with no output schema, the description compensates by naming the returned outputs (coupon, probabilities, greeks, scenario grid, payoff data) and the payment mechanics. Only the preview_note relationship is left unaddressed.

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% and the single termSheet param has a rich inline example, so the baseline is already 3. The description adds semantics by enumerating supported product types and the returned quantities (coupon/participation, probabilities, greeks, scenario grid), going beyond the schema.

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 ('structured-note pricing for crypto') and enumerates the product types it handles (autocallable, barrier reverse convertible, range accrual, principal-protected, shark fin). It doesn't distinguish itself from the sibling preview_note, so it stops short of a 5.

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?

Clearly says to send a JSON term sheet on BTC/ETH/SOL and explains the free-preview vs paid full-quote flow, plus what happens on an unpaid call. It does not explicitly route an agent to preview_note or name when-not-to-use, so no 5.

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