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

Annotations cover the safety profile (readOnlyHint, openWorldHint), and the description adds genuinely useful context: the read is live via eth_call (no caching/staleness assumption) and enumerates the returned fields. It does not cover error behavior (invalid address, non-ERC-20 contract) or any rate limits.

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?

One dense sentence, front-loaded with the resource and chain, then the return shape and read mechanism. Every clause carries information; nothing is padding.

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?

No output schema exists, so the description has to carry return-value semantics, and it does (raw units, decimals, symbol, formatted amount). With only two fully-documented required params and annotations covering safety, the remaining gap is failure-mode behavior, which is minor.

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 both parameters are already documented with their address patterns; baseline 3 applies. The description loosely reinforces that 'token' is an ERC-20 contract on Base via the USDC/WETH examples, but adds no format or constraint detail 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?

States a specific verb (retrieve balance) and resource (ERC-20 token balance of a wallet) and pins the chain to Base mainnet, which cleanly separates it from the solana_* siblings. The token examples (USDC, WETH, any token) make the scope unmistakable without opening a 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?

Usage is only implied by the resource name; the description never states when to use this versus siblings like base_token_info, nor any preconditions (e.g., must be an ERC-20 contract, not an NFT or native ETH). An agent can infer the obvious case but gets no routing help.

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