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 well: it discloses that the call is paid ($0.002 USDC on Base or Solana), requires no account or API key, that failed calls are not charged, and that data comes from DefiLlama live pools. It does not describe pagination behavior or the shape of returned rows beyond "APY and TVL," which keeps it from a 5.

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 description is dense and front-loads the paid status and the resource scope before pricing and access details. The literal URL is somewhat redundant with the tool name but is useful operational context; every other clause (price, chains, no key, no charge on failure) earns its place.

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, no-output-schema, paid data tool, the description covers the things an agent most needs before invoking: cost, payment chain, auth requirements, failure billing, and data provenance. The main residual gap is what a result row looks like and how many rows come back by default, which the limit parameter partially covers.

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 sort, limit, and min_tvl_usd are already documented in the schema, and the description adds only the implicit link that APY/TVL are the sortable metrics. No extra syntax, units, or interaction between parameters (e.g. how min_tvl_usd affects row count against limit) is provided, so the 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?

The description names a concrete resource and scope: live pools holding OSETH across protocols and chains, returning APY and TVL from DefiLlama. An agent can tell this apart from the many buy_yields_chain_* and buy_yields_protocol_* siblings by the token-specific scope. It stops short of explicitly naming which sibling to use for a chain-level or protocol-level view, so it is clear but not fully differentiated.

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?

"Where to earn yield on OSETH" implies the use case (find yield opportunities for a specific asset), and the price/payment details tell the agent what it costs to call. There is no explicit when-to-use versus alternatives guidance, e.g. no pointer to buy_yields_chain_* when the user wants a chain-wide view, so usage must be inferred from the token scope.

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