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

Beyond readOnlyHint, destructiveHint=false, and openWorldHint, the description discloses pricing ($0.01/call via x402 USDC or card key, first 25 free, failed calls free) and repeats are not refunded; that is critical context given idempotentHint=false. It also states the limits and meaning of the nonce (outgoing transactions only, not transfer or trading history) and that the call changes nothing.

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 text is front-loaded with the scope and the alternative tools, then the returned data, then the pricing. It is dense but nearly every clause carries distinct information; the parenthetical chain of alternatives and the long token list make it slightly heavy, but nothing is truly 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 carries the burden of explaining the return values, and it does list them: balances, nonce, and account classification. It omits details such as units, decimals, or the response shape for the extra tokens, but for a read-only snapshot tool it is close to complete.

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 100%, so the baseline is 3, but the description adds real meaning: the tokens parameter accepts up to 20 extra ERC-20 addresses in addition to the built-in majors, it enumerates those majors, and it gives a format example for the address. It stops short of describing how the two parameters interact when a token address duplicates a built-in one.

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 gives a specific verb and resource: ETH and major token balances for an address on Base, plus the account nonce and whether it is an EOA, a contract, or an EIP-7702 account. It names the exact token set and explicitly separates itself from wallet_balances (all 5 chains) and wallet_portfolio (USD values), so an agent can tell them apart without opening a 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?

It opens with the scope constraint 'Base only' and names the two alternatives together with the condition that selects each of them (all chains, USD values). It also gives a concrete scenario, 'check a counterparty's holdings', and an example address, so the agent knows when to use this tool and when not to.

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