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

With no annotations at all, the description carries the full behavioral burden and does disclose the most consequential trait: this is a paid call at $0.02 USDC (or prepaid credits) and the payment credentials must go in MCP request headers (X-Payment / X-Payment-Tx / Authorization: Bearer fg_…), not in the arguments. That is real, actionable context an agent would otherwise get wrong. It still says nothing about rate limits, whether the full leaderboard is truncated, or how the limit argument caps results.

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 text is duplicated near-verbatim in Chinese and English, and the return-field inventory is also repeated, roughly doubling length without adding information. It opens with a quoted conversational question instead of a front-loaded statement of what the tool returns, so the most useful content is buried mid-paragraph.

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 filterable leaderboard with seven optional parameters and no output schema, the description does state the full shape of the returned record (APY breakdown, rewards share, TVL, IL risk, trends, quality score, risk flags) and the payment mechanics. The notable remaining hole is per-parameter semantics, which is scored separately.

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% across 7 parameters, so the description must supply meaning, and it does not — it merely recites the parameter names (chain, project, stable, min_tvl, min_apy, max_apy, limit). No units, formats, defaults, or semantics are given (e.g. is min_apy a percentage or a fraction? is limit a row cap?). The phrase "参数同左" adds nothing.

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 resource and verb clearly enough: a full leaderboard of yield pools covering chain, protocol, symbol, APY split (fees vs incentives), reward share, TVL, IL risk, 7d/30d trend and risk flags. That is more specific than the tool name alone. However it never distinguishes this from the sibling 'yield-pools.pool_now', and the opening is framed as a user question ("Ask 'what are the highest yield stablecoin pools'") rather than a statement of function.

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 leading example question implies the use case (ranking stablecoin pools by APY), which is a reasonable usage cue. There is no guidance on when NOT to use it, no mention of the sibling pool_now for single-pool lookups, and no statement about when to prefer narrower filtered queries over the full leaderboard.

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