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

Annotations already cover read-only, idempotent, open-world and non-destructive semantics, so the description is not required to restate them. It adds genuinely non-schema information: the $0.001/call cost and the projected response shape. It does not disclose defaults or behavior when no asset is supplied, which keeps it short of a 5.

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?

It leads with a dense, cryptic field-shape dump (best_by_asset[] {asset, best {...}, best_base_only}, usdc_by_chain[]...) before the actual usage sentence. The actionable guidance is buried at the end, and the leading pseudo-schema is hard to parse without an output schema to compare against.

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 sketching the return fields is justified, and the cost disclosure is a plus. However, for a two-parameter optional-input tool the description omits min_tvl semantics, defaults, and empty-result behavior, which leaves an agent unable to reason about the most likely filtering use case.

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 only 50%: asset is documented ('USDC, USDT, DAI…') but min_tvl is bare. The description never explains min_tvl (presumably a TVL floor filter), nor what happens when asset is omitted, nor defaults for an optional-parameter tool. The phrase 'per chain' implies a chain selector that the schema does not have, adding potential confusion.

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 result: the single best stablecoin yield per asset or chain, and contrasts it against defi_yields for the full pool list. An agent can distinguish it from siblings without opening the schema. Slightly muddied by mentioning 'chain' as a grouping dimension when no chain parameter exists.

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?

Explicit routing: 'Use for the single best stablecoin yield per asset or chain; for the full pool list use defi_yields.' This names both the when and the alternative sibling, leaving nothing to inference.

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