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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds genuinely useful context: a $0.005 USDC x402 price on eip155:8453, and the concrete set of proxy standards detected including legacy ZeppelinOS (USDC). It stops short of describing response shape or failure modes (e.g. what happens for an address with no code on an unsupported chain).

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 core question, then capability detail, then pricing – a sensible ordering with no filler. The only waste is the near-verbatim repetition of the title as the opening clause, which costs a few tokens without adding information.

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 steps in to name the returned fields (EOA vs contract, code size, hash, proxy slots, native balance, nonce) and the payment requirement, which is enough to call it correctly. Missing only error/edge-case behavior and multi-chain semantics for chains without code.

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 50%: `chain` already has its allowed values documented inline and `address` has a regex pattern, so the schema carries most of the weight. The description adds only the loose phrase 'on a chain' and does not explain the address format, chain-id fallback, or default behavior, so it neither compensates nor detracts.

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?

Opens with a concrete question the tool answers ('Is an address a contract or a wallet?') and then enumerates the specific resources it inspects: bytecode, code size/hash, EIP-7702 delegations, EIP-1167 minimal proxies, EIP-1967 implementation/admin/beacon slots. This clearly separates it from siblings like evm_address, evm_balance and evm_token, which don't inspect bytecode.

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?

The framing question implies when to reach for it (classifying an address), but there is no explicit when-not guidance and no routing against siblings. Notably it also returns native balance and nonce, overlapping evm_balance, without saying which tool to prefer for balance-only lookups.

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