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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the bar is lower. The description adds useful context beyond annotations: data source ('reads directly from chain via RPC multicall') and return format ('raw balance in wei and formatted human-readable'). No contradiction with annotations.

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?

Three sentences, each with a distinct function: what it does, when to use it, and what it returns. The primary purpose is front-loaded and every sentence earns its place with no filler.

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?

Combined with complete parameter descriptions, strong read-only annotations, and an output schema, the description covers the essential invocation context: purpose, preconditions, data source, and return format. Nothing critical is missing for correct selection and usage.

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 description coverage is 100%, so the baseline is 3. The description reinforces that token_addresses are ERC20 contract addresses and mentions raw vs formatted balances, but it adds no substantive parameter-level meaning beyond the schema.

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 a specific verb and resource: 'Get native ETH and ERC20 token balances for a wallet address.' It clearly distinguishes this tool from the many read_account_* and read_asset_* siblings by focusing on wallet balances and explicitly mentioning the RPC multicall read mechanism.

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 concrete, actionable guidance: use before write_account_add_liquidity or write_account_deposit to verify sufficient tokens. It does not explicitly compare against other read_* alternatives, but the stated use cases make selection unambiguous without exclusions.

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