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

Annotations already declare readOnly, non-destructive, openWorld and non-idempotent; the description adds genuinely new behavior: revert yields a 422 with the reason and is uncharged, each successful call is billed at $0.01 (first 25 free), and repeats are not free. The billing-per-call note is consistent with idempotentHint=false and 'changes nothing' is consistent with readOnlyHint=true.

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?

Purpose and usage are front-loaded, the example is compact, and every sentence carries information. The pricing/payment sentence is long and operationally dense, but it is relevant because calls are charged, so 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 tells the agent what comes back (gas units, gwei and ETH) and how failures surface (422 with reason, uncharged). For a 4-parameter read-only estimator that is everything needed to call it correctly.

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, but the description adds conditional semantics the schema does not: value is expressed in ETH and from is only needed 'when the call depends on it'. It also frames data as calldata for a contract call, reinforcing the schema wording.

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 ('Estimate the gas a transaction would use on Ethereum') and names the RPC method. It also implicitly distinguishes itself from the parallel arb_/base_/op_/polygon_ variants by naming Ethereum and explicitly routes gas-price-only queries to eth_gas.

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 ('before sending a transaction or to price a batch') and an explicit alternative with its selection condition ('for the gas price alone use eth_gas'). No inference is required to choose between the two.

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