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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: the 5-year maximum span, the 12-month default, and that results are historical closes rather than forecasts. It does not say what happens when neither product nor metal is supplied (0 required params makes that callable) or when both are supplied, leaving the most error-prone invocation path unspecified.

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?

Three compact sentences, front-loaded with what the tool returns, then how to call it, then when to use it, closing with a one-clause scope caveat. No filler and no restatement of the title.

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?

An output schema exists so return values need no explanation, and the description covers both invocation modes, defaults, and the span cap. The remaining gap is the zero-required-parameter case: nothing states which mode wins when both inputs are omitted or both are provided, which matters for a tool where the schema enforces no exclusivity.

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 meaning the schema lacks: from/to apply only to the metal mode, the default window is the last 12 months, and the total span is capped at 5 years. It does not clarify whether product and metal are mutually exclusive at the schema level (no oneOf present), which is the key ambiguity for the two-input case.

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?

Names the resource (price history) and clearly splits it into two modes: a product's past check/wire prices versus a metal's daily closes. The 'past data, not a forecast' line distinguishes it conceptually from get_spot_prices and get_premiums, though it never names the current-price sibling explicitly, so the agent must infer which one to pick for 'what's gold today'.

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?

Gives an explicit trigger for the metal mode ('when the user asks how a metal's price has moved over a past period') and states the default window. It offers no equivalent when-to-use cue for the product mode and no explicit exclusion telling the agent to use get_spot_prices for current prices, which is the most likely confusion given the sibling list.

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