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

With no annotations, the description carries the full disclosure burden and does add real behavioral context: it lists the returned fields (supply APY, borrow APY, utilization, reward APY, per-asset best-rate summaries) and discloses a per-call cost of $0.005 USDC. What it omits is the payment mechanics (wallet/auth requirements) and any rate-limit or failure behavior, so it falls short of fully covering a paid, unannotated tool.

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?

Four compact sentences, front-loaded with the comparison scope and protocols, followed by return contents, filtering, and price. No filler or repetition; each sentence contributes distinct information.

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?

Since there is no output schema, the description must explain return values and it does so explicitly (APY types, utilization, reward APY, per-asset best-rate summary). The remaining gap is payment/auth mechanics for a paid call, which an agent would need to know before invoking.

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%, with both parameters documented including example values and 'omit for all' semantics. The description restates the same asset/protocol examples without adding new syntax, casing rules, or validation detail, so it meets but does not exceed the schema baseline.

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 ('Compare lending and borrowing rates') and enumerates the exact protocols covered (Kamino, MarginFi, Drift, Solend, Save, Mango). This clearly separates it from sibling tools like yield_rates, lst_yields, and l2_yield_scanner, which address different yield surfaces.

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 description tells the agent how to narrow results ('Filter by asset ... or protocol'), implying it is the tool to reach for when comparing lending markets. However, it never states when to prefer it over yield_rates or lst_yields, nor any exclusions, so the routing decision is left to inference.

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