get_withdrawal_fees

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

Annotations only assert readOnlyHint=true and openWorldHint=false. The description adds substantive behavior: per-venue route listing, fees in native units AND USD from a dated price snapshot, suspended-wallet marking, cheapest-open-route naming, venue ranking with a best pick and savings figure, plus the critical semantic that fees are exchange-charged pass-through costs (dynamic at Kraken/KuCoin) rather than trading fees.

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 trigger conditions before capabilities, which is the right ordering for retrieval. It is long, and the Chinese/English duplication roughly doubles the length, but each block serves a distinct audience and no sentence is pure padding.

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 still specifies what is returned (routes per venue, native and USD fees, suspensions, cheapest route, ranked venues with a best pick and savings). Combined with the fee-semantics caveat and the sibling handoff, an agent has everything needed to call and interpret this read-only lookup correctly.

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 asset, country, network, language and exchanges in detail, including network aliases and the language enum's limited scope. The description largely restates the covered asset and network lists, adding only the note that Coinbase lists just BTC/ETH/USDT/USDC with dynamic fee estimates — a minor increment over structured data, so the 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 (get) and resource (withdrawal fees) and enumerates the exact questions it answers — cheapest network, per-asset per-chain fees, venue network support, on-chain transfer cost comparison. It explicitly distinguishes itself from compare_total_cost, which covers the all-in cost of a trade, so an agent can separate it from siblings without opening any schema.

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 concrete when-to-use triggers in two languages (moving coins to a wallet or another exchange, comparing on-chain costs) and names the alternative tool plus the condition that selects it ('for the all-in cost of a trade use compare_total_cost instead'). This is explicit routing, not implication.

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