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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description usefully adds that the response includes spotAsOf, the basis and deductions in plain English, and that county unlocks a postal arrangement page — genuine return-shape context — but says nothing about freshness, caching, or failure modes for an unlisted carat.

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 sentences with the core definition front-loaded and no filler; the county and carat instructions follow in a logical order. Slightly packed ('one metal and carat or fineness') but nothing wasted.

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 naming the returned figures (spotAsOf, basis, deductions) and the county-dependent extra content. Coverage of all three inputs plus the return shape makes it sufficient for correct invocation, though pricing freshness and error behavior remain 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 description coverage is 100%, so the schema already documents all three parameters, including the 'omit for every grade' rule and the county slug examples. The description restates those same points without adding new syntax, formats, or defaults, so baseline 3 applies.

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 and resource: the net price Liffey Metals pays today in euro per gram, scoped to 'one metal and carat or fineness'. The singular scope implicitly separates it from the plural sibling get_buy_prices, but the description never names that sibling, so differentiation is left to inference.

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?

Offers parameter-level guidance ('give the seller's county to add that county's postal arrangement and page'; 'omit carat for every grade'), which implies how to use it, but gives no when-to-use-this-vs-alternatives routing despite siblings get_buy_prices, get_sell_price and estimate_payout being obvious candidates.

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