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

Annotations already declare read-only, idempotent, closed-world, non-destructive behavior. The description goes beyond that by disclosing the payment-method rule (check/wire from $1,000, otherwise card/PayPal at +5%) and that totals exclude shipping and tax — real behavioral context an agent couldn't infer from annotations.

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-loads the outcome (what fits the budget), then the key constraints and goal options. A single dense paragraph with no filler, though the payment-method clause is packed tightly and slightly interrupts the flow of what is returned.

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 explained, and the description still usefully names the returned fields. Mutation risk is nil and annotations cover safety; the only minor gap is that the budget's min/max is left to the schema.

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 67% and the enums are self-explanatory, so baseline is 3. The description adds meaning for the 'goal' enum (what each goal optimizes for) but doesn't clarify the $25–$5M budget bounds, which live only in the schema.

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 ('plan a budget') and enumerates exactly what it returns: product, piece count, assumed payment method, total, and premium over spot. This clearly distinguishes it from siblings like find_bullion (product search) or get_premiums (premium lookup).

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 clear context for when to use it: allocating a fixed USD budget toward a metal, with goal options ('lowest premium, popular coins, or gift-friendly items'). It also scopes the result ('before shipping and tax'), which tells the agent to use estimate_sales_tax separately, though that routing is implied rather than named.

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