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

Annotations already declare non-read-only, non-idempotent, open-world, non-destructive, but the description goes well beyond them: it explains WHY readOnlyHint is false (each call is charged), documents pricing and payment paths, and states failure semantics ('malformed addresses rejected with 400, uncharged', 'failed calls free'). That is exactly the extra behavioral context a charged, stateful-looking call needs.

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 operation, scope, and ordering, then payment/pricing and failure rules in terse clauses. Every sentence earns its place — the pricing and 400-rejection notes are not padding for a paid endpoint.

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 supplies the return shape (direction, counterparty, amount, transaction), ordering (newest first) and cap (up to 50), plus cost and failure behavior. Given the tool's complexity and its absence of an output schema, an agent has everything needed to call it and interpret the result.

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 the schema already documents token (0x ERC-20, default USDC) and blocks (1-2000, default 1000). The description restates those same ranges and defaults rather than adding syntax or edge-case meaning, so per the high-coverage baseline this is a 3. The only genuinely new constraint, the 'up to 50' result cap, is an output property rather than a parameter.

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 — 'List a wallet's recent transfers of one ERC-20 token (default USDC) on Optimism, in and out' — plus scope (last N blocks, newest first, up to 50). It explicitly names op_token_balance as the tool for a different question, so an agent can distinguish it from siblings 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 concrete when-to-use triggers ('confirm a payment arrived or see what was sent') and names the alternative with the condition that selects it ('for the current balance use op_token_balance'). Nothing is left to inference.

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