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

Annotations already establish readOnly, idempotent and non-destructive, so the safety profile is covered. The description still adds real context - execution by the service's own Reth node, 'Nothing is signed or written', and the return field list - which goes beyond the annotations. No contradiction with openWorldHint=false.

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-loads the core mechanism, then when/when-not, then returns - a good ordering with little waste. Slightly dense with back-to-back parentheticals and a long Returns list, but every clause carries information.

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 correctly compensates by enumerating return fields (ok, contract, function, selector, output_type, value, value_human). Together with the schema and use-case guidance this is nearly complete for a 7-parameter tool; minor ambiguity remains around how 'function' labels interact with a supplied selector.

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 86%, so the baseline is 3. The description adds meaning beyond the schema by explaining the two calling modes: built-in ERC-20 function labels versus arbitrary calls requiring a 4-byte selector plus ABI-encoded parameter, which is not stated in the property descriptions.

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 ('Read-only (eth_call) against any Ethereum contract') plus the built-in ERC-20 helpers and the raw selector path. This is sufficient for an agent to distinguish it from adjacent read tools like eth_get_account or tron_read_contract without opening the 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 when-to-use scenarios ('an on-chain value without trusting a third-party API - a USDT/USDC balance, token decimals, an allowance') and explicit exclusions ('Do not use: to send a transaction, or for a historical balance'). The agent has nothing to infer about applicability.

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