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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real behavioral context: it emits fine content and unit rates, a prefilled PDF-report link, and can incorporate what it calls 'current website quotes'. Note the mild tension: live website quotes sit oddly against openWorldHint=false, though this reads as bundled data rather than a true contradiction.

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 tight sentences, front-loaded with the computation and followed by the extras (quotes, PDF link, custom spot, mixed lots). No filler, though 'unit rates' and 'Includes current website quotes' are slightly ambiguous as written.

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 needn't be described, and the description does signal breadth (single items, mixed lots, offer comparison, PDF report). For a 12-parameter tool with a oneOf lot structure and near-zero schema documentation, however, it leaves too much inference for correct invocation of the karat/fineness, gold-filled, and dental paths.

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 only 8% (just assayBasis and measuredGrams), so the description must carry parameter meaning, and it largely does not. It names metal/purity/weight/construction, custom spot, and mixed lots, but leaves the consequential semantics unexplained: when to use basis=karat vs fineness, how purity is interpreted under each, what layerDenominator does for gold-filled items, how fees/offer are applied, and which unit values are accepted.

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 opening clause names a specific verb+resource (melt value, fine content, unit rates, buyer-offer comparison) and the inputs that drive it (metal, purity, weight, construction). It is clearly distinct from calculate_exchange or find_coins, but it never names the closest sibling calculate_coin_value, and the schema's coin-lot variant blurs that boundary further.

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: mention of an 'optional buyer-offer comparison' and 'custom spot prices' hints at when to supply those inputs, but there is no explicit when-to-use statement, no prerequisites, and no routing guidance versus calculate_coin_value or calculate_penny_nickel.

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