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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description goes beyond that by disclosing the required auth header format (Authorization: Bearer sk_...), the fact that the address mode is unauthenticated, and the x402/Permit2 payment context that gives the returned allowance meaning.

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?

Two sentences, front-loaded with the default keyed behavior before the `address` alternative, with no redundant filler. It is dense — the parenthetical auth header interrupts the balance list — but every clause carries 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?

There is no output schema, so the description carries the return-value burden and does so by enumerating both modes' outputs (available balance, account balance, held amount, budget left, chain balances, allowance). For a single-optional-param read tool with annotations present, this is essentially complete.

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 already 100%, so the baseline is 3, but the description adds real meaning: the `address` parameter switches to a keyless mode and changes both the semantics and the returned fields (on-chain USDF/USDG, Permit2 allowance) rather than just trimming the response.

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 names the specific resources returned: the calling key's available balance, the account balance and held amount, the key's budget remaining in USDF, plus a second mode returning a wallet's on-chain USDF/USDG and Permit2 allowance. That is precise enough to distinguish it from payment siblings like quote or x402_pay, though it never names a sibling explicitly.

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 a clear conditional for choosing the `address` mode over the keyed mode ('With `address` instead, no key'), which is useful mode-selection guidance. It does not explain when an agent should call balance at all versus siblings such as receipt, so overall usage guidance remains implied rather than explicit.

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