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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely new operational context: a metered cost of 0.01 USDC on Base x402 and the X-Provider-Key header for customer-owned credentials. It does not state the response shape or any failure/settlement behavior, keeping it short of a 5.

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?

Two tight sentences, front-loaded with the computational result and followed by the commercial/auth facts. Nothing is padded, though "where needed" is vague enough to blur when the header is actually required.

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 one-parameter, no-output-schema tool the description does the necessary work: it enumerates the three outputs (drawdown, peak/trough, recovery status) and discloses payment and auth preconditions. The remaining gap is input encoding, which the description leaves unresolved while the schema points back to a description that never supplies it.

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?

There is one parameter with nominal 100% schema coverage, so the baseline is 3. The description adds only that the curve consists of caller-supplied equity values; it does not resolve the schema's own deferral to an "operation description" for units and format, so the integer/timestamp encoding of equity_curve remains unexplained in both places.

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 a specific verb ("Compute") and resource ("maximum historical drawdown, peak/trough positions and recovery status"), so the agent knows exactly what output to expect. It does not, however, distinguish itself from adjacent finance siblings such as api_finance_cagr, api_investment_return, or api_finance_position_risk.

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 only implied: "from caller-supplied equity values" tells the agent what input this tool expects, which frames the use case. There is no explicit when-to-use/when-not guidance and no routing to alternative finance tools, so selection still requires inference from sibling names.

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