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

Annotations already declare readOnly/destructive/openWorld, and the description adds real context on top: returned fields (raw amount, decimals, symbol, human-readable amount), error codes for missing or non-ERC-20 contracts, that failures are uncharged, pricing via x402 or credits, and that repeats are charged (consistent with idempotentHint=false). It stops short of describing pagination/edge cases like unverified tokens, so it is strong but not exhaustive.

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?

A dense but well-ordered paragraph: what it returns, when to use it, the sibling alternative, input/error semantics, then cost. Nearly every sentence carries a fact an agent needs, though the pricing and repeat-charging sentences could be trimmed without losing selection-relevant 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?

For a two-parameter read tool with no output schema, the description supplies everything needed: output shape, alternative tool, address format, error behavior with charges, and cost model. The only gap is the ticker-vs-address tension, which is minor against the overall coverage.

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. The description adds the 40-hex-character format constraint, which is useful, but its claim that 'both inputs are 0x addresses' conflicts with the schema, which allows the token parameter to be a ticker such as USDC or WETH — an agent could wrongly assume a ticker is rejected.

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+resource (ERC-20 token balance of a wallet on zkSync Era) and immediately bounds scope: token holdings, not the native coin. It names the sibling zksync_balance as the tool for the native coin, 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?

Gives an explicit use case (check holdings before a transfer or trade) and an explicit routing rule: 'for the native coin use zksync_balance.' It also states acceptance criteria for inputs and the failure semantics (404/422, uncharged), which is well beyond implied usage.

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