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

With no annotations, the description carries the full burden and does: it discloses data provenance ('GoPlus + explorer event logs, each re-read onchain'), the ranking heuristics (unlimited, unknown spender, unverified or non-contract spender, flagged), the exact return payload shape (to, data, chainId, value 0), and degradation behavior ('partial results if a chain fails'). It also states cost ($0.02), which is the kind of operational detail agents need and rarely get.

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 key verb and scope, and the two trailing sentences (per-chain status, partial results, cost) earn their place as distinct facts. The main sentence is long and packs a nested parenthetical about data sources, which slightly hurts scannability but contains no filler.

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 and no annotations exist, so the description has to do the work — and it largely does, enumerating the risk categories and the revoke-transaction fields returned. What's left underspecified is the exact result envelope (how per-chain status is structured, whether approvals are nested per chain, ordering guarantees) for what is clearly a multi-object response.

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 0% and the single parameter is an unlabeled 'address' with only a regex pattern. The description compensates partially by establishing that the address is an EVM wallet swept across seven EVM chains, which usefully rules out Solana-style addresses given the solana_* siblings. It does not say whether checksummed or lowercase input is expected, but the schema pattern covers that gap.

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?

Starts with a specific verb and resource ('One call sweeps a wallet') and enumerates the exact chains, the two approval classes covered (ERC-20 allowances, NFT setApprovalForAll), and the output (ready-to-sign revoke tx). This clearly distinguishes it from the many single-chain siblings like base_token_approvals or ethereum_token_approvals without any schema inspection.

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 phrase 'One call sweeps a wallet on Base, Ethereum, BNB...' establishes the aggregate multi-chain context, which implicitly frames when to pick this over the per-chain *_token_approvals siblings. However, it never names an alternative or states a when-not condition (e.g. 'use base_token_approvals for a single chain'), and the $0.02 cost is stated without guidance on when that trade-off is worth it.

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