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

With no annotations, the description carries the full burden and does well: it discloses the paid x402 requirement ('$0.02 USDC on Base'), the pool-coverage limitation (deepest WETH/USDC pools only), and the content of the response (trades, volume, net flow, top wallets). It stops short of stating per-call vs. session billing, rate limits, or error behavior.

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?

A single front-loaded sentence that opens with purpose and then enumerates returns and cost with no filler. The long clause listing output fields is justified because there is no output schema to carry that 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 no output schema and no annotations, the description supplies the return shape, the pool-coverage constraint, and the payment model — enough to call it correctly. Minor gaps: behavior when no qualifying trades exist and whether the $0.02 is charged per invocation or per result set.

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 token/minUsd/limit/minutes are already documented with ranges and defaults. The description adds only the qualitative framing ('last N minutes', 'largest trades', 'deepest pools'), which reinforces but does not extend the schema — baseline 3 applies.

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+resource ('Whale and large-trade tracker for an ERC-20 on Arbitrum One') and scopes it to buy/sell activity in the token's deepest WETH/USDC Uniswap v3 pools over a look-back window. The chain qualifier plus 'whale/large-trade' framing separates it cleanly from the parallel eth_/base_/optimism_/polygon_ large_trades siblings and from snapshot/profile tools.

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 gives useful context — only the deepest WETH/USDC pools are covered and only recent activity within N minutes — which implicitly frames what the tool is and isn't for. But it never names an alternative (e.g., arbitrum_token_snapshot for aggregate metrics) or states an explicit when-to-use / when-not-to-use condition, leaving routing to inference.

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