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

With no annotations at all, the description carries the full burden and does well: it discloses the tool is paid, the exact price and payment chains, that no auth/API key is required, and that failed calls are not charged. It also names the upstream data source and enumerates the returned metrics. What is missing is rate-limit/retry behavior and freshness/latency of 'live' data, which matters for a paid call.

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.' — the single most important fact for an agent deciding whether to call — followed by what the data is, then cost/access terms, then the endpoint URL. Telegraphic, zero filler sentences, though the fragmented style and embedded URL make it slightly denser than ideal reading.

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 an all-optional, 3-parameter read tool with no output schema and no annotations, the description supplies what an agent needs: cost, payment path, auth model, charge-on-failure policy, data provenance, and the shape of returned values. Only secondary details (rate limits, refresh cadence, empty-result behavior) are absent, which is acceptable here.

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 documents sort (tvl default / apy), limit (1-100, default 20), and min_tvl_usd (default 100000). The description only echoes the sort dimension via 'top pools by TVL or APY' and never mentions limit or the TVL floor, so it adds little beyond the schema. Baseline 3 applies.

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 specific verb and resource ('Live DeFi yields on Bob') with the exact scope ('top pools by TVL or APY') and the returned fields (base/reward APY, TVL, 7d APY change). The chain name 'Bob' and the data source (DefiLlama) let an agent distinguish it from the ~35 sibling buy_yields_chain_* tools 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?

Payment and access conditions are clear ($0.002 USDC on Base or Solana, no account or API key, failed calls not charged), which implies this is a paid data call to prefer only when Bob-chain yields are actually needed. However, there is no explicit when-to-use/when-not guidance and no routing to alternatives such as buy_yields_top or buy_yields_protocol_*, leaving selection vs siblings to inference.

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