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

Annotations already declare readOnly/destructive=false, but the description adds substantial context the annotations cannot: error semantics (404 for no contract, 422 for non-ERC-20), that failed calls are uncharged, the $0.01/call x402 pricing with first 25 free, and the warning that repeats are billed. This is consistent with idempotentHint=false, where a naive reader would otherwise assume a read is free to repeat.

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 with purpose and return shape, then routing, then error/pricing caveats — good ordering with no filler sentences. It is dense and semicolon-heavy, packing pricing, errors and idempotency into one long clause, which costs some readability.

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 return payload itself (raw amount, decimals, symbol, human-readable amount) and covers the two realistic failure modes plus billing. An agent has everything needed to call it, interpret the result, and anticipate a 404/422.

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% and both params are documented there, so the baseline is 3; the description earns a bump by restating that both inputs are 0x 40-hex addresses and that `token` accepts either a ticker or a contract address. It adds validation detail beyond the schema text but no examples of token resolution edge cases.

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: ERC-20 balanceOf for a wallet on Linea, including the exact token set (USDC, USDT, WETH or any token) and the return fields. It explicitly separates itself from linea_balance (native coin) and implicitly from linea_allowance/linea_token_info, so an agent can pick the right sibling 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?

"Use to check stablecoin or token holdings before a transfer or trade" gives a concrete use context, and "for the native coin use linea_balance" names the specific alternative and the condition that selects it. Nothing essential is left to inference for a read-only balance lookup.

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