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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), yet the description goes further: it discloses a possible one-time DefiLlama cache refresh side effect, the kill-switch behavior (health still answers, refresh skipped), the YH_STALE_DEGRADE_SECONDS staleness trigger, and the non-custodial/no-key/no-transaction guarantee.

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 purpose and return contents, then operational caveats. Efficient overall, though the closing 'Research estimates only — non-custodial' line is somewhat boilerplate and could be trimmed.

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?

Despite no output schema, the description enumerates the return payload (status, schemaVersion, scoringVersion, feature flags, available tools) and explains the stale-data refresh path, so an agent knows both how to call it and what to expect back.

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?

Zero parameters, which yields the baseline 4. The description still supplies an example input ({}) confirming the empty call shape, adding light value over the empty schema.

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+resource ('Liveness and capability check for yieldhunter') and immediately enumerates what it returns. It also carves out its role as the entry-point tool distinct from list_yields and the scoring siblings.

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?

'Use this first to verify connectivity' and 'Copy-paste path starts here, then list_yields' give explicit ordering guidance and name the follow-on sibling. No explicit when-not-to-use clause, but the entry-point framing is unambiguous.

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