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

Annotations already declare readOnlyHint and openWorldHint, and the description adds material behavioral context on top: a $0.002 per-successful-call charge, the x402 payment rails (Base, Solana, Arc), and that failed calls are free. It does not describe pagination or latency, but for a single-read tool the pricing/charge semantics are the valuable disclosure.

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?

Three tight sentences, front-loaded with what is returned, then the scoping caveat, then cost. No filler and 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?

With an output schema present, the description needn't enumerate return fields, yet it still characterizes the output (name, symbol, decimals, raw/human amount, conditional USD) and covers cost and chain default. Sufficient for correct invocation; only the terse sibling pointer to the native-balance path leaves a slight gap.

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 documents chain (with default), token (ERC-20 contract, 0x…), and address (EVM, 0x…). The description adds only that the amount is raw and human and that USD appears only when Coinbase has a spot price; it does not enrich the parameter meanings 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 (read balance) and precise resource (ERC-20 balance of an address for one named token contract on a chain), and explicitly disambiguates scope by noting only the named token is read and that the native balance lives elsewhere.

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 clear context boundary: 'Only the token you name is read; the native balance is in /api/evm/address.' This tells the agent when this tool is and isn't the right one, though the alternative is referenced as an API path rather than a sibling tool name, so routing takes a small inference.

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