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

Goes well beyond the annotations: a non-answering network is reported as an error rather than failing the whole call, the call is charged ($0.002, first 25 free, failed calls free) and repeats are not free — which is the key non-idempotence implication. It also restates the no-side-effects guarantee, consistent with readOnlyHint/destructiveHint.

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 action and network scope, then routing guidance, then failure behavior, then cost. Dense but every clause carries information; the pricing/credits tail is slightly long but is genuinely decision-relevant for a paid tool.

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 still explains what comes back (per-network native and USDC balances, USDC total, per-network error entries) and what it costs. For a single-parameter read tool with annotations already covering safety, nothing an agent needs before calling is missing.

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% and there is only one parameter, so the schema already carries the load; the description adds a concrete example address that clarifies the expected 0x format. It doesn't add more than that, which is appropriate at this coverage level.

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 and resource ('Read a wallet's native coin and USDC balances') plus the exact scope (five named networks, one call, plus USDC total). It explicitly distinguishes itself from <chain>_token_balance and wallet_portfolio, so an agent can pick it without opening any 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 a positive trigger ('Use to find where a wallet's funds are before a payment or bridge') and two explicit alternatives with the conditions that select them: single token/single network → <chain>_token_balance, all tokens on Base → wallet_portfolio. When-not guidance is concrete rather than implied.

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