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

Annotations declare readOnly, openWorld, idempotent, and non-destructive. The description adds critical non-obvious behavior: it is a paid x402 endpoint ($0.003 per call), returns a paid request object with response schema and example rather than data directly, requires calling the URL with an x402 or MPP client, and refuses bad input before charging. This is rich disclosure beyond 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?

Front-loads the use case and supported assets, then payment mechanics, then routing alternatives. Every sentence adds useful information, though 'One wallet across several chains' is slightly redundant; overall well-structured but not maximally tight.

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, but the description explains exactly what is returned (a paid x402 request with response schema and example), how to use it, pricing, and error behavior. Combined with annotations covering safety and idempotency, an agent has everything needed to invoke and follow through.

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 address and chains are already documented in the schema. The description adds output scope (which tokens and chains are covered) but no new parameter syntax or constraints, so the baseline of 3 applies. The chains default and address format remain schema-provided details.

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 balances) and resource (wallet's token balances across multiple chains), lists supported tokens and chains, and names three sibling alternatives for narrower or wider use cases. An agent can distinguish it from evm_erc20_balance, evm_native_balance, and wallet_balance_batch without opening schemas.

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?

Explicitly says 'Use when you need...' and gives concrete alternatives: one token on one chain -> evm_erc20_balance; native coin on one chain -> evm_native_balance; many wallets -> wallet_balance_batch. This is direct routing guidance with clear conditions.

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