calculate_savings

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

Annotations already declare readOnlyHint and openWorldHint=false, so the safety profile is covered. The description adds real context beyond that: it lists the factors that affect the computation and, with no output schema present, discloses the return payload (savings amount plus the referral link to register). It stops short of describing defaults, fallbacks, or error behavior.

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?

The trigger is front-loaded and every clause earns its place, but the Chinese and English trigger sentences are duplicated, which is redundant text for a token-constrained context. Still appropriately sized for an 18-parameter computational tool.

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?

For a complex 18-parameter tool with no output schema, the description covers purpose, trigger, computation basis, and a minimal return summary. It omits the richer narrative output (advice/warnings/tradeoffs/reasons implied by the language parameter) and default/fallback behavior, but the exhaustive schema fills most of the remaining gap.

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% across all 18 parameters, so the schema already carries the semantics. The description only restates a subset (volume, trade type, VIP tier, token discount, funding cost) and lists token symbols, which adds marginal value over the schema rather than compensating for any gap.

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 description states a specific verb+resource: computes fee savings from registering via a referral link, and enumerates the drivers (volume, trade type, VIP tier, token discount, funding cost). It is clearly distinguishable from generic fee tools, though it does not explicitly name siblings like get_referral_link or calculate_annual_cost even though it also returns a referral link.

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?

It gives an explicit trigger in both languages: 'Use when the user asks how much they can save on fees by registering via a referral link.' This is a clear condition for invocation, but no when-not-to-use or alternative tool routing is provided.

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