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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the bar is for added context, and this description goes far beyond: it discloses response metadata fields (chainsCovered, chainsNotCovered, chainsNotServed), conditional flags that 'appear only when set, so a reserve with none of them is not flagged', the v3/v4 coverage asymmetry, the percent-unit convention, and that identical APYs across spoke rows 'are expected rather than duplicates'. Nothing contradicts the annotations.

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?

Long but with zero filler: every sentence addresses a distinct misinterpretation risk (coverage semantics, empty-result trap, APY ranking, conditional flags, spoke/hub duplicates, per-reserve swap semantics). The purpose is front-loaded in the first sentence, and the trade-off against response size ('hundreds of kilobytes') justifies behavior rather than padding prose.

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 carries the full burden of explaining return values — and it does: row shape under 'reserves', paired supplyApyPct/borrowApyPct fields, per-version fields (suppliable/borrowable vs availableLiquidity/totalSuppliedUsd), the user param's row additions (walletBalance, youCanSupply, youCanBorrow), and chain coverage metadata. For a 21-chain, two-version listing tool with no output schema, this is complete.

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 100% with already-strong param descriptions, so the baseline is 3. The description adds genuine cross-parameter semantics: passing symbols changes v3 coverage from Ethereum-only to all chains, omitting chainId triggers the chainsCovered/chainsNotCovered metadata, and the Pct-suffix naming convention. This is additive, but the schema still carries most per-parameter load, so not a 5.

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?

Opens with a specific verb+resource+scope: 'List Aave markets/reserves (symbol, APY, caps, liquidity) on v3, v4, or both.' It names the entities, the data dimensions, and the version axis, and it differentiates from siblings by explicitly contrasting canSwapFrom with what get_swappable_tokens answers per chain.

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 explicit when-to-use directives with conditions: 'to compare one asset across chains, pass symbols and no chainId', 'Pass it [user] whenever the question is about what someone can actually do rather than what the rates are', and the symbols param's 'Strongly preferred when you know the asset' guidance. It also warns when NOT to trust results ('an empty result for one of them is not an answer about that chain') and names the alternative tool (get_swappable_tokens).

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