What to weigh besides the rate

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

Annotations already cover read-only, non-destructive, open-world operation, so the bar is lower. The description still adds real behavioral context: missing-data signals report null and are excluded from weighting rather than guessed, weights are exposed so the score can be recomputed, and the output is backward-looking only.

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 purpose and use case are front-loaded in the first sentence, and the remaining text is spent enumerating the six signals and the null-handling rule, each of which earns its place given there is no output schema. No filler sentences.

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?

With no output schema, the description carries the full burden of explaining return values, and it does: score range, band values, the signals object contents, per-signal raw value and sub-score, method.weights, and null behavior. An agent can call this and interpret the response without further information.

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 coverage is 100% and the single `pool` parameter is fully documented in the schema with format examples. The description only indirectly scopes it ('one Morpho vault or Aave reserve'), so it adds little beyond what the schema already provides; 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 resource and scope: a risk profile for one Morpho vault or Aave reserve, returned as score, band and a signals breakdown. It is clearly distinguishable from the sibling yield tools (list_base_yields, best_yield, yield_history), which surface rates rather than risk.

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?

Gives a clear usage context ('for use before committing capital') and an explicit pairing rule ('Pair with `yield_history` for an unusually high rate'), which routes the agent to a sibling. It also bounds expectations with 'Describes what has happened, not what will,' but offers no explicit when-not-to-use case.

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