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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description still adds real context beyond them: per-call pricing ($0.01 via x402 or card key), a 25-call free tier, failed calls free, malformed addresses rejected with 400 and uncharged, and a 50-result cap ordered newest first. The note that repeats are not free is consistent with idempotentHint=false rather than contradicting it.

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?

Purpose and scope are front-loaded in the first clause, followed by usage routing, then error and pricing details. It is a single dense paragraph where nearly every clause carries information, though the pricing/free-tier detail crowds the block and slightly dilutes the core instruction.

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 responsibly names the returned fields (direction, counterparty, amount, transaction), the ordering (newest first), and the 50-row cap. Combined with annotations and a fully described schema, an agent has everything needed to call it correctly; only result pagination/truncation semantics are left implicit.

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 both optional parameters already document their defaults and the 1-2,000 block range in detail. The description largely restates those defaults; the only added value is an example 0x address demonstrating expected format. Baseline 3 is appropriate when the schema carries the parameter burden.

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 ... on Optimism, in and out'), including the scope (last N blocks), default token, and max results. An agent can distinguish it immediately from op_token_balance and from the per-chain variants like eth_token_transfers.

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 concrete use case ('confirm a payment arrived or see what was sent') and names the alternative with its condition ('for the current balance use op_token_balance'). The exclusion is explicit, so the agent does not have to infer which sibling to pick.

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