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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds substantive context beyond them: the read is at the latest block, results come in both wei and ETH, malformed addresses are rejected with 400 and not charged, pricing is $0.002/call with the first 25 free and failed calls free, and repeats are not free because each call is billed. The pricing/charging detail also operationalizes the otherwise puzzling idempotentHint=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?

The description is front-loaded with the core capability, then alternatives, error behavior, example, and pricing in a logical order with no filler. The clause 'reads or computes only and changes nothing' partially restates readOnlyHint, but the remaining sentences all earn their place given the pay-per-call model.

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?

For a single-parameter read tool with no output schema, the description covers everything an agent needs: what is read, on which chain, at which block, in which units, what the address must look like, what happens on bad input, what it costs, and which siblings handle adjacent needs.

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?

With one parameter at 100% schema coverage, the schema already documents the address field. The description still adds value by constraining the format to 0x addresses, stating that malformed input is rejected with 400 rather than silently failing, and supplying a concrete example address. It stops short of noting contract-address behavior or checksum requirements, keeping it off 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?

The description names a specific verb and resource (native ETH balance of a 0x address), pins the chain (Arbitrum One), the underlying call (eth_getBalance), the block (latest), and the units returned (wei and ETH). It explicitly distinguishes itself from arb_token_balance and wallet_portfolio, so an agent can route correctly 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?

It gives a concrete use case (check whether a wallet can pay gas or a transfer) and names both alternatives with the condition that selects each: arb_token_balance for ERC-20, wallet_portfolio for all holdings at once. That is explicit when-to-use plus when-to-use-something-else.

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