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

Goes well beyond the readOnly/idempotent annotations: discloses one Multicall3 eth_call per chain at a stated block, on-chain symbol/decimals resolution, raw+decimal return shape with a nonzero summary, absence of USD prices, and the full x402 payment flow (unpaid call returns PaymentRequired; retry via params._meta['x402/payment']) at $0.003 USDC per call.

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?

Purpose and chain scope are front-loaded, and pricing/payment mechanics are grouped afterwards. The first sentence is overloaded with four chained clauses, but given the tool's complexity there is little pure waste.

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 covers return values (raw and decimal amounts plus a nonzero summary), chain and token coverage, block semantics, and the payment handshake needed to actually invoke it. Nothing an agent needs to call it successfully is missing.

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: it explains that tokens= requires a single chain=, that token symbol/decimals are resolved on-chain, and that gnosis/celo are non-default. Some of this (the 20-token cap, the default chain list) duplicates 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 precise verb and resource ('Typed balances for one address: native coin plus USDC, USDT, WETH...') along with exact chain scope and a custom-token mode. The stated exclusions ('No USD prices', on-chain symbol/decimals) implicitly separate it from metadata/snapshot siblings like token_info or wallet_snapshot.

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?

Clearly presents two usage modes: the default curated token set across six chains, or 'pass chain= and tokens= (up to 20 addresses) for your own list', with gnosis/celo noted as on-request. It does not name when to prefer a sibling tool or state when not to use this one.

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