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

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing the paid model ($0.002 USDC per successful call over x402 on Base, Solana or Arc, failures not charged) and the source limitation that no audit or exploit-history data exists in this free feed. It also lists what each result row carries (TVL, 7-day impermanent loss, reward share of APY, IL-risk flag), which tells the agent what to expect behaviorally.

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 the ranking behavior and result fields, then the safety caveat, then cost — a sensible priority order with little filler. The one wasted element is the malformed sibling reference sentence, which is cut off mid-thought and costs more attention than it returns.

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?

For a five-parameter, read-only tool with a 100% covered schema, an output schema, and annotations, the description covers purpose, ranking basis, data provenance, pricing, and known limitations. Minor gaps remain: no statement of data freshness, and no note on behavior for unrecognized chain names, though the schema's 'as DefiLlama spells it' hint partially covers the latter.

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%, so the schema already documents chain, limit, maxApyPct, minTvlUsd and stablecoinOnly, including the useful note that extreme APYs are usually reward-token artefacts. The description restates the filter set (chain, minimum TVL, stablecoin-only) but adds no syntax or defaults beyond the schema, and never mentions limit or maxApyPct, so the 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 verb and resource — 'Ranks DeFi pools by total APY from DefiLlama's public yields data' — plus the filter dimensions and the per-pool fields returned. It also explicitly disclaims what it is not ('Ranking is by APY, not by safety: there is no audit or exploit-history score'), which prevents confusion with safety-scoring siblings like agent_intel_token_composite_safety_score.

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 use context (yield discovery with chain/TVL/stablecoin filters) and one explicit exclusion that routes to agent_intel_mev_sandwich_risk_analyzer for sandwich-attack profit. The routing sentence is truncated and awkward ('for a swap of a given.'), and no guidance is offered against other closely related siblings such as agent_intel_stablecoin_peg_integrity_radar or agent_intel_token_liquidity_migration_watch.

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