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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered by structured fields; 'reads or computes only and changes nothing' largely restates them. The description does add genuinely new behavior: a 422 with the revert reason for failing transactions, failures uncharged, and per-call pricing that explains why idempotentHint=false ('repeats are not free'). That added cost and error semantics is worth real credit but is thinner than the runtime/auth detail a 4-5 would require.

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 core purpose and the sibling routing come first, then parameters, then error and pricing terms. It is information-dense and every sentence carries content, though it runs long for a four-parameter read tool and 'reads or computes only and changes nothing' is partly redundant with the readOnlyHint annotation.

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 takes on the burden of describing return values and does so in concrete units. It also covers error behavior (422 plus reason), cost and payment prerequisites (x402 USDC, card key, free tier), which is everything an agent needs to decide whether and how to call it.

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 the baseline is 3 and the schema already documents all four parameters. The description adds some meaning beyond it: value is denominated in ETH, calldata is for a contract call, and 'from' is only needed when the result depends on the sender — that last clause is a real semantic hint the schema does not give (the schema only says 'default: an empty address').

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 Unichain'), names the underlying RPC method (eth_estimateGas), and enumerates the return units (gas units, gwei, ETH). It is explicitly differentiated from the sibling unichain_gas, so an agent can pick correctly without opening either 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 before sending a transaction or to price a batch; for the gas price alone use unichain_gas' gives both the triggering context and the alternative with the condition that selects it. It also explains when to supply optional inputs ('the sender when the call depends on it'), which is usage guidance, not just schema restatement.

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