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

Goes well beyond the annotations (readOnly/openWorld/non-idempotent/non-destructive): latest-block evaluation, no tx or gas, 8 KB calldata ceiling, revert yields 422 with the reason and is uncharged, $0.01/call with 25 free, and the explicit warning that repeats are charged because nothing is cached. That is exactly the operating context an agent needs.

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 the operation and its constraints; every sentence carries information (semantics, limits, error behavior, pricing). It is a dense single block rather than segmented, and the pricing sentence is somewhat long, but nothing is truly wasted.

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 still covers the return value (raw return data, decode via ABI) and the failure mode (422 with revert reason). Given a simple 3-parameter tool, an agent has everything needed to call it and interpret the response.

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%, so baseline is 3; the description adds a concrete worked example (to=0x1d17...38D4, data=0x18160ddd for USDC totalSupply) and the 8 KB limit on calldata, plus the reminder that the returned bytes need ABI decoding. The optional `from` parameter for msg.sender checks is not addressed, keeping it short of a 5.

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: read-only eth_call on zkSync Era that sends ABI-encoded calldata to a contract and returns raw return data, with no transaction or gas. It also routes away from siblings by scoping itself to view functions that have no dedicated tool (e.g. zksync_token_balance, zksync_balance), so an agent can tell it apart.

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?

Explicitly says to use it for any view function lacking a dedicated tool, and instructs decoding the result with the function's ABI. The 'when not' case (prefer the dedicated tool when one exists) is implied rather than named, and no specific sibling is called out.

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