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

With no annotations, the description carries the burden and does disclose meaningful behavior beyond the schema: supported chain set, the 20-token-per-call cap, and the exact return payload shape (raw and decimal-adjusted amount, symbol, decimals). It omits error/auth behavior, so it is strong but not exhaustive.

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?

A single dense sentence, front-loaded with the resource and input forms, followed by the return shape and the usage cue. No filler, though the colon-chained clause structure packs a lot into one sentence and the multi-token list format is left implicit.

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?

An output schema exists, so return values need not be explained (though the description helpfully summarizes them). For a 3-parameter read tool the coverage is nearly sufficient; the remaining gaps are the parameter defaults and the syntax for batching up to 20 tokens.

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 0%, so the description must compensate, and it does: tokens accepts a contract address or the symbols USDC/USDT/DAI, address accepts a wallet or ENS name, chain is constrained to five named networks. It does not state the defaults (ethereum, USDC) or how multiple tokens are delimited, leaving a small 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?

States a specific verb+resource ('Balance of any ERC-20 token') and enumerates the exact input forms (contract address or USDC/USDT/DAI symbol), the wallet identifier types (address or ENS), and the five supported chains. This clearly separates it from siblings like evm_wallet_balance (native), erc20_token_info, erc20_allowance and erc20_transfers.

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?

The trailing 'Use before transfers, swaps or payments' implies a usage context but gives no exclusions or named alternatives among the many sibling balance/price tools. An agent gets a hint about the moment to call it but must still infer when to prefer erc20_token_info, crypto_token_prices, or evm_wallet_balance instead.

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