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

With no annotations, the description carries the full burden and does much of it: it discloses the cost ($0.005/call), the accepted payment assets and chains, the payment handshake, and the atomicity guarantee (all reads at one block via Multicall3). It omits behavioral edges an agent would want — read-only nature, behavior on invalid addresses, retry/reuse of a signed payment, or rate limits — so it is strong but not complete.

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?

Dense but well front-loaded: capability and limits come first, then price, then the payment procedure. Every sentence carries information, though the payment-asset enumeration (USDC on Arc/Base/Solana, XNT on X1) is heavy for a description and could be trimmed.

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 paid, mutating-handshake tool with no annotations and no output schema, the description covers invocation well but never says what comes back — per-address balance mapping, partial failures for bad addresses, or whether the block number is returned. Those gaps matter when output schema is absent, so it is adequate rather than 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, and the description adds real meaning beyond it: the hard 50-address ceiling and the constraint that all addresses share a single token (native coin or one ERC20), which the schema's 'optional ERC20' wording does not convey. It adds nothing extra for chain or payment beyond what the schema already says.

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 and resource (bulk wallet balances), the exact scope (up to 50 wallets, one chain, native coin or one ERC20, one block via Multicall3), and the four supported chains. This clearly differentiates it from the single-address siblings evm_wallet_balance and evm_token_balance without the agent needing to open either 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 explicit operational context: use it when you need up to 50 balances at a single block, and a precise two-step payment procedure ('call once without payment for the terms, sign them, call again with payment'). It stops short of naming the single-wallet alternative or stating when not to use the bulk form (e.g. for one address), which keeps it from a 5.

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