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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safe-read profile is covered. The description usefully adds the public DefiLlama data source and a non-advice disclaimer, but says nothing about data freshness, rate limits, or response shape beyond the APY/TVL mention.

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?

Three tight sentences, front-loaded with what is returned and where the data comes from, followed by filtering and the disclaimer. No filler.

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?

There is no output schema, so the description must hint at return contents, which it does by naming APY and TVL alongside chain/kinds. That is enough for an agent to call it correctly; only pagination/freshness details are absent, which are minor for a read-only list.

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%, including enum semantics for kind, defaults for limit, minTvlUsd, and sortBy, so the schema carries the parameter burden. The description only gestures at "filter by chain or kind" and adds no syntax or units beyond what the schema states, so the baseline of 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 verb (Lists) and resource (tokenized real-world asset deployments), with concrete examples (treasuries, credit, funds) and named output fields (APY, TVL). This clearly separates it from siblings like list_stablecoin_yields and list_tokenized_equities.

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?

"Filter by chain or kind" gives implied usage, and the DefiLlama provenance plus "information only, not advice" frames intent. However, it never says when to prefer this list tool over siblings such as get_rwa_asset for a single asset or rwa_market_summary for aggregates, so routing 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.