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

Annotations only cover readOnlyHint and openWorldHint, but the description adds the critical non-structured behavior: $0.002 USDC per call over x402, failed calls are free, and omitting `payment` returns a quote that must be signed and resubmitted. That payment/auth handshake is exactly the kind of trait annotations cannot express.

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 and clearly partitioned into purpose, pricing, when-to-use, alternatives, parameters and returns. Slight redundancy: return contents (first/last/high/low/percent change) appear in both the opening paragraph and the 'Returns' line, costing a little space without new information.

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 compensates by describing the return payload precisely (points[] with time, price_usd, Chainlink round, plus first, last, high, low and percent change) and covering the paid-call flow end to end. An agent has everything needed to call and interpret this tool.

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%, so the baseline is 3, but the description adds real meaning beyond the schema: the asset must have a Chainlink USD feed (narrowing valid symbols), points are 'evenly spaced' prices, and the payment quote-then-sign flow is restated in prose. It stops short of explaining edge cases such as what happens when fewer than `points` rounds exist in the window.

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 (past USD prices for a crypto asset) with concrete scope: up to 365 days, up to 100 points, sourced from Chainlink's on-chain Ethereum feed. It explicitly distinguishes itself from the sibling token_price, so an agent can route correctly without opening either schema.

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?

Includes explicit 'When to use' (trend, high/low, change over a period for a major asset) and 'Use instead' naming token_price for the current price of any token, including those without a Chainlink feed. The condition that selects the alternative is spelled out, not inferred.

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