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

No annotations are supplied, so the description carries the full burden — and it does meaningful work: it declares the tool is paid, the exact price ($0.01 USDC), accepted payment chains (Base or Solana), that no account or API key is needed, and that failed calls are not charged. That is exactly the kind of commercial/behavioral context annotations cannot express; only the response format and any rate limits are left unstated.

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?

Compact, front-loaded with 'Paid.', then purpose, then metrics, pricing, auth requirements, billing policy and endpoint. Dense fragments rather than sentences, but every clause carries information and nothing is redundant.

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, the description compensates by enumerating the return fields (APY, TVL, 7d APY change) and the source (DefiLlama), and it covers the payment/auth model fully. For a 3-optional-parameter read tool this is close to complete; only pagination and empty-result behavior are unaddressed.

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% and all three parameters (sort, limit, min_tvl_usd) are documented in the schema with defaults and ranges. The description adds nothing about them — notably it does not say that results are sorted by TVL by default or that a minimum-TVL filter is applied automatically, which would have explained the default result set.

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 concrete verb and resource: live DeFi yields for the Maple protocol, listing the returned metrics (APY, TVL, 7d APY change) and the data source. The protocol is named explicitly, which is what separates it from the hundreds of buy_yields_protocol_* siblings, but the description never says so — an agent must infer the distinction from the tool name alone.

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?

Usage is only implied: an agent reading 'Live DeFi yields for maple' can infer it should call this when it wants Maple pool yields. There is no explicit when-to-use vs. when-not, and no pointer to the chain-scoped or token-scoped alternatives (buy_yields_chain_*, buy_yields_token_*) for a different slice of the data.

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