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

With no annotations supplied, the description carries the full behavioral burden and does well: it discloses a paid call at $0.005 USDC on Base or Solana, no account or API key required, failed calls not charged, and that the data originates from DefiLlama. It does not describe the response shape or result ordering, which matters somewhat since there is no output schema.

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." followed immediately by the purpose, then commercial terms, then a reference URL — an efficient ordering with no filler. The final URL is useful provenance rather than padding, though "No account, no API key." and "Failed calls not charged." could be compressed into one clause.

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 zero-required-parameter read-only query with full schema coverage and no output schema, the description covers purpose, data source, price, payment chains, auth requirements, and failure billing — everything needed to decide and invoke. The one real gap is the absence of any indication of the response structure or ordering, which the agent must discover by calling.

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%, so the schema already explains sort (tvl default or apy), limit (1-100, default 20) and min_tvl_usd (default 100000). The description adds only an indirect hint by naming APY and TVL as the data dimensions; it gives no extra meaning about defaulting, ranges, or how filtering interacts with sorting. Baseline 3 is appropriate.

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 STEAKUSDC: live pools holding STEAKUSDC across protocols and chains, APY and TVL" states the exact resource and the returned metrics, and the token naming mirrors the token-scoped sibling tools (buy_yields_token_steth, buy_yields_token_usdc, etc.). It stops short of an explicit verb like "list" and never names a sibling, so differentiation comes mostly from the tool name.

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 opening phrase "Where to earn yield on STEAKUSDC" implies the usage context (yield-pool discovery for this specific asset), and the surrounding family makes the token/chain/protocol alternatives inferable from names. However, there is no explicit "use this when..." statement, no exclusion of adjacent tools (buy_yields_chain_*, buy_yields_protocol_*, buy_yields_stablecoins), and no guidance for the sort/min_tvl trade-off.

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