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

With no annotations, the description carries the full burden of disclosing behavior, and it does so thoroughly. It states that the current reading is withheld past a 'lending freshness ceiling' and the response says 'stale', while the settled series is always readable. It explains that APY is what borrowers pay, not a promise, and that the app's headline rate is not measured. It also notes that data is captured every 10 minutes, providing temporal granularity. These are concrete behavioral traits beyond any schema or annotation.

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 a single long sentence with many clauses, but it is well-structured with parentheticals and a colon, effectively organizing distinct pieces of information. Every phrase adds value: markets, aggregates, series, staleness, APY semantics, exclusions, and a disclaimer. It is dense but not verbose; it earn its place. A slight improvement could be breaking it into shorter sentences, but the current form is efficiently packed.

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?

The description covers a wide range: what markets are included, how the aggregate is computed, the series frequency, staleness behavior, the meaning of APY, and exclusions. It also mentions key fields like marketsWithoutApy and stockCollateralShare. However, it does not explicitly describe the response structure (e.g., whether the series is an array of timestamps and values), and it doesn't mention pagination or error cases. Given the complexity and lack of an output schema, it is quite complete but leaves minor gaps in the expected return format.

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?

The tool has zero parameters, and the schema is an empty object with 100% coverage (meaning the schema is fully described, i.e., empty). Baseline for no parameters is 4. The description adds context about what the tool returns, which is more than necessary for parameters but helps set expectations for the output. Since there is no parameter semantics to clarify, the score aligns with the 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?

The description clearly identifies the tool's subject (Robinhood Earn as observed on Morpho) and enumerates the data it provides (USDG-loan markets, aggregates, 7-day series). It is distinct from sibling tools by its specific scope, even though it lacks an explicit verb like 'retrieve' or 'show'. The description reads as a detailed specification rather than a tautology, so it exceeds a basic statement but stops short of the crispness of 'display Robinhood Earn data'.

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 implies usage for Robinhood Earn data on Morpho, but it does not explicitly state when to choose this tool over siblings like get_lending_markets or get_stock_premiums. It does provide some exclusions: it notes the app's headline rate after vault fee is not measured, and that APY is not a promise, which helps an agent understand what the tool is not for. However, no alternative tools are named, so the guidance is implicit rather than explicit.

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