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

Beyond the readOnlyHint=true and idempotentHint=true annotations, the description discloses concrete behavioral details: it handles rate limits and partial failures, returns null for failed reads rather than misleading zeros, counts failures, errors if every read fails, and reports the block height of the snapshot. This is exactly the kind of context agents need to interpret results correctly.

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 first sentence is a front-loaded, high-signal summary. The rest is organized into clear sections (motivation, supported chains, when to use/not use, args, return example) with no redundant padding. Every sentence earns its place, and the length is justified by the tool's complexity.

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 carries full responsibility for explaining return values; it provides a complete JSON example with all fields, including edge-case behavior (null for individual failures, 'failed' count, error condition for total failure). It also covers defaults, supported chains, and limits, making it fully sufficient for an agent to invoke and interpret this tool 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?

The input schema already covers 100% of parameters with descriptions, so the bar is at 3. The description adds extra semantic nuance: 'Duplicates removed, order preserved' for addresses, the exact default token behavior (canonical USDC), and a structured output example that shows how token decimals are scaled to produce clean balances. This extra context earns a 4.

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 opens with 'Read an ERC-20 token balance for up to 500 wallet addresses in a SINGLE call', which clearly states the verb (read), the resource (ERC-20 token balance), and a key distinguishing scope (bulk, up to 500 addresses). It also distinguishes from sibling tools like onchain_portfolio or onchain_cross_chain_balances by focusing on ERC-20 balances for a list of holders on a single chain.

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 description explicitly provides 'When to use' (portfolio roll-ups, airdrop checks, holder analysis) and 'When NOT to use' (native ETH balances, historical blocks), giving the agent clear selection criteria. It also contrasts with manual eth_call batching, implying this is the efficient bulk alternative.

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