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

With no annotations at all, the description carries the full load, and it does disclose useful traits: a read-only eth_call path, the full return shape (raw + decimal balance, symbol, decimals, block), and a price point ($0.001 USDC). It says nothing about failure modes — non-ERC20 token, unverified contract, unsupported chain string — or whether the price applies per call, which matters for a metered tool.

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-loaded and dense: purpose and mechanism first, return shape second, a concrete example third, price last. No filler sentences; the only slack is that the example format uses non-JSON notation, but that is a minor stylistic cost for the clarity it buys.

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?

No output schema exists, and the description compensates well by enumerating the returned fields, and the chain list plus pricing round it out. The unresolved wallet-vs-address ambiguity and the absence of any error/edge-case behavior keep it from being complete for a 4-parameter tool.

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 0%, so the description must define the four parameters, and it only partially does via the example: address = wallet, token = token contract, chain = chain identifier. The fourth parameter, "wallet", is never mentioned and sits alongside "address" as an apparent duplicate with no explanation of which to use or what happens if both are supplied.

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 names a specific verb+resource ("ERC20 token balance") and pins down the mechanism (balanceOf via eth_call) and the supported chains (Base/Ethereum/Arbitrum/Optimism/Polygon). This implicitly separates it from chain_balance (native asset), chain_erc20_transfers, and token_metadata, but it never names a sibling to route against.

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 chain list and the worked example give a clear picture of when this applies, but there is no explicit contrast with chain_balance, chain_live_balance, or wallet_balances, which is the main ambiguity an agent faces in this crowded chain_* family. Usage is implied rather than stated.

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