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

No annotations exist, so the description carries the full burden, and it discloses several non-obvious traits: a per-call price ($0.005 USDC via x402 on MCP tools/call, $0.01 direct HTTP), the signals the verdict is derived from (APY 1d/7d/30d, stability forecast, il7d, sigma, outlier flag, TVL), and the Base-chain constraint on the token parameter. It does not cover failure behavior for invalid poolIds, latency, or caching.

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?

Purpose and output shape are front-loaded, and the long middle sentence is a compact enumeration of inputs rather than filler. The pricing and routing note is useful but slightly crowded into the same block; a small tightening would make it a 5.

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 and no annotations, the description responsibly covers the return contract (verdict enum, risk score range, field-cited reasons) and the cost model. Remaining gaps are edge-case handling and routing to the preview variant, which keep it below a 5 for a paid, non-read-only-flagged tool.

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 already 100%, so the baseline is 3, but the description adds real meaning: 'pool' must be the 'pool' field from defi_yields (a concrete provenance hint), and 'token' is an optional 0x address on Base that only adds a honeypot-check pointer rather than changing the verdict. That clarifies the effect of each parameter beyond the schema's own text.

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 and resource ('per-pool DeFi yield-entry go/no-go') and defines the exact output artifact: a SUSTAINABLE | DECAYING | OUTLIER | AVOID verdict plus a 0-100 risk score. It explicitly contrasts with the sibling defi_yields, which supplies the raw pool data this tool consumes, so an agent can pick between them without opening either schema.

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 sequencing rule: 'The should-I-enter-THIS-pool call after defi_yields,' which tells the agent when to invoke it and what must precede it. It also notes the direct HTTP route as an alternative transport. It stops short of mentioning the yield_entry_verdict_preview sibling or stating when not to use the tool (e.g. non-Base tokens, missing poolId).

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