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

Beyond the annotations (readOnly/idempotent/openWorld), the description discloses genuinely useful operational facts: a hard cap of 20 transfers, the inclusion of block range and pricing caliber boundaries, per-call cost, and that payment credentials must travel in MCP headers (X-Payment / X-Payment-Tx / Bearer) rather than as parameters. That auth-channel warning is exactly the kind of context annotations cannot express.

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 first sentence is well front-loaded, but the body repeats the same vendor-asset facts twice in Chinese and English, and again partially in the opening line ("up to 20 large transfers" appears three times in effect). Significant trimming is possible without losing any 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?

For a paid, open-world read tool with no output schema, the description covers the essentials: what comes back, the 20-row ceiling, cost, and how payment is transmitted. What it omits is parameter-level detail (chain vocabulary, token identifier format, min_usd units), which matters because the schema provides none.

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 0% — the four properties carry only bare titles. The description merely restates the parameter names (token, chain, blocks, min_usd) and adds one hint that blocks means "recent N blocks." It never says what chain values are accepted, whether token is a symbol or contract address, or what unit min_usd uses, so it fails to compensate for the coverage 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?

The opening line gives a concrete verb+resource framing ("who just moved a large amount of this token") and enumerates the returned fields (USD, from, to, tx, block), so an agent knows exactly what this tool produces. It does not, however, explicitly differentiate itself from siblings like whale-flow.whale_now or whale-flow.whale_top5_entry — the word "full" hints at a fuller list but never names an alternative.

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 question-style phrasing ("Ask 'who just moved a large amount of this token'") implies the triggering scenario, and the price disclosure ($0.09 USDC per call) helps an agent weigh cost. There is no explicit when-not guidance, no named alternative for smaller lists or live snapshots, and "参数同左" (args as above) is circular rather than instructive.

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