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

The description adds substantial context beyond annotations: no transaction or gas, 8 KB calldata limit, 422 on revert with the reason and no charge, $0.01 per call, first 25 free, and failed calls free. It also explains that reads change nothing but repeat calls are not free, which aligns with idempotentHint=false rather than contradicting it.

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?

The description is front-loaded with purpose and usage, then pricing and behavioral constraints. It is dense but mostly earns its space; the USDC selector is given twice (once parenthetically and again in the example), which is a minor redundancy.

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 explains that the return value is raw return data to be decoded with the function ABI. It also covers revert behavior, charging, calldata limits, and lack of transaction/gas, which is complete for this read-only call 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 already 100%, so the schema documents to, data, and from. The description adds useful meaning with a concrete to/data example, the ABI selector format, and the instruction to decode results using the function's ABI, though it does not elaborate on the optional from parameter.

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 states a specific verb and resource: a read-only contract call on Ethereum, with the exact eth_call semantics of sending ABI-encoded calldata and receiving raw return data. It distinguishes itself from dedicated tools by saying to use it for view functions that have no dedicated tool, and the chain name separates it from sibling *_call tools.

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?

It clearly says when to use this tool: for any view function without a dedicated tool, with a concrete USDC totalSupply example. It does not enumerate the sibling alternatives such as eth_token_balance or eth_balance, but the 'no dedicated tool' condition gives an agent enough routing guidance.

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