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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), and the description adds genuinely new operational facts: this is a paid call at $0.08 USDC (or prepaid credits), and the payment proof must arrive in MCP request headers (X-Payment / X-Payment-Tx / Authorization: Bearer fg_…), explicitly not in parameters. That header-placement warning is exactly the kind of behavior an agent cannot get from annotations and would otherwise get wrong.

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 lead sentence is well front-loaded and information-dense, but the [zh] and [en] blocks restate the same commercial and payment facts almost verbatim, and the vendor asset name is repeated in both. The duplication may serve multilingual agents, but it roughly doubles length for the same content.

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 parameters and no output schema, the description compensates by enumerating the returned fields and explaining the payment/auth precondition, which is enough to call it correctly. It stops short of stating ordering or tie-breaking for the ranking and whether results are cached, but nothing critical for invocation is missing.

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?

The schema declares zero parameters, so the baseline is 4, and the description confirms this explicitly with 'Args: none' / '入参：无'. It also clarifies that the payment material is header-borne rather than an argument, which closes the only plausible parameter ambiguity for a paid tool.

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 description names the concrete question the tool answers and the exact resource: the top-10 stablecoin pools by risk-adjusted yield, with the returned fields enumerated (TVL, spot APY, 30d mean APY, IL risk, exposure type, smart_score plus its five components). It also positions itself against the sibling top20 by stating 'Entry tier: half the board. The full 20-pool ranked board is $0.10,' so an agent can separate the two tiers without opening a 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?

It gives an explicit triggering question ('which stablecoin pool has the best risk-adjusted yield') and names the fuller alternative (the 20-pool board at $0.10), which is real when-to-use guidance. It does not address the other siblings (top5, by_chain), so routing among those tiers 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.