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

With no annotations supplied, the description carries the full burden and does so well: it discloses that the call is paid ($0.002 USDC on Base or Solana), that no account or API key is needed, that failed calls are not charged, and that data is live from DefiLlama. What it omits is rate limits, latency/freshness cadence, and any error/retry semantics beyond the billing policy.

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?

Front-loaded with "Paid." so cost is the first thing an agent sees, followed by purpose, price/payment, auth, billing policy, and endpoint URL. Every clause carries information, though the middle sentence is a dense run-on that could be split for scannability.

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, parameterless-required read endpoint with no output schema and no annotations, the description covers purpose, returned fields (APY, TVL), data provenance, cost, payment rails, auth requirements, and failure billing. Nothing an agent needs to decide whether to call it or to expect the charge 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?

All three parameters (sort, limit, min_tvl_usd) have complete schema descriptions including defaults and value hints, so the schema does the heavy lifting. The description adds no parameter-level meaning such as how TVL filtering interacts with the "live pools" claim or whether sort=apy excludes low-TVL noise. Baseline 3 applies at 100% coverage.

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?

"Where to earn yield on BNB: live pools holding BNB across protocols and chains, APY and TVL" gives a specific resource (yield pools per token) plus the returned metrics and data source. It is clearly distinct from the chain-level (buy_yields_chain_*) and protocol-level (buy_yields_protocol_*) siblings, but it never distinguishes itself from the near-identical buy_yields_token_wbnb sibling, leaving an ambiguity an agent cannot resolve from the text.

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 framing "where to earn yield on BNB" implies the use case (finding BNB yield opportunities) but gives no explicit when-to-use, when-not-to-use, or named alternative such as the wrapped-BNB or BSC-chain variants. Usage is inferable rather than stated.

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