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

Annotations indicate readOnlyHint=true and openWorldHint=true, but the description adds critical behavior: the tool is paid ($0.01 USDC) and returns a 200 with found:false for EOA/empty code. It also discloses the payment address and that it uses public RPC. This goes beyond annotations, providing cost, error handling, and network context without contradiction.

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?

The description is a single, dense sentence but every clause serves a purpose: purpose, cost, network, invalid-address behavior, exclusions, and payment. It is front-loaded with the core purpose and avoids redundancy. It could be split for readability, but remains concise and efficient.

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 successfully conveys the return content (name, symbol, decimals, totalSupply) and the invalid-address case. It also covers cost and payment details. Missing are specifics on response format (e.g., JSON structure) and any rate limits, but these are not critical for a simple metadata fetch tool; the description is sufficiently complete for correct invocation.

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?

The schema covers the parameter fully with a description of '0x-prefixed 20-byte ERC-20 contract address on Base'. The tool description reinforces that 'address= required' and notes behavioral nuance: EOA/empty code returns found:false. This adds value by explaining how the parameter affects the response, which schema alone does not convey.

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 clearly states the tool fetches ERC-20 metadata (name, symbol, decimals, totalSupply) for a given address on Base via public RPC. It also explicitly excludes spot price and wallet balance, directly distinguishing from siblings 'price' and 'who'. The verb-resource pairing is unambiguous.

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?

The description provides explicit exclusions: 'Not a spot price (use /price)' and 'Not a wallet balance (use /who)', which directs agents to appropriate alternatives. It also states the required parameter 'address'. While it doesn't elaborate on when to use this tool positively, the negative guidance is strong and covers the main alternative scenarios.

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