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

Annotations already carry readOnlyHint=true and destructiveHint=false, and the description does not contradict them, so this is not a mere annotation echo. It adds substantial behavioral context beyond annotations: the Pct-suffix percent convention ('3.32' means 3.32%), the v4 hub-wide sharing of utilisation and the rate curve, the warning that collateralFactorPct is the liquidation boundary itself, and the double-counting warning for liquidityFeePct (supplyApy = borrowApy x utilisation x (1 - liquidityFee)). These are exactly the non-obvious facts an agent needs to interpret results correctly.

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?

The description is long (~300 words), but nearly every sentence carries a non-obvious fact an agent could not infer from names like 'collateralFactorPct' or 'liquidityFeePct'. It front-loads the core purpose and scoping first, then layers the field interpretations. It could trim the parenthetical 'if you want to check' formula, but overall the density of useful content earns its length.

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, the description carries the burden of explaining the return data, and it does so extensively: percent units, v4 hub-wide behaviour, the two ambiguous v4 fields, and the price fields with their source. Minor gaps remain — it does not enumerate every v3 vs v4 difference or describe the cap structure in the same depth as the risk parameters — but for a 5-parameter, zero-output-schema tool with substantial domain complexity, it is close to 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 description coverage is 100%, so the baseline is 3. The description's parameter-related contribution is thin: it explains the v3/v4 selector pattern and that version is optional when the selector is unambiguous, but the schema itself already documents each parameter (including 'copied verbatim' for reserveId). Most of the description's semantic depth concerns output fields, not parameters, so it does not exceed the schema-covered baseline.

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?

The description opens with a specific verb and resource: 'Deep detail for a single reserve (rates, caps, risk parameters, utilisation, the interest-rate curve, token addresses) on v3 or v4.' This immediately distinguishes it from sibling list-style tools like get_markets, and the sentence 'get_markets quotes no price at all, so what an asset is worth on Aave is answered here' explicitly separates its scope from a sibling.

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 when-to-use and sequencing guidance is present: 'Use get_markets first to get the reserveId (v4) or market+token (v3).' It also gives an exclusion rule ('get_markets quotes no price at all') and warns about the collateralFactorPct misunderstanding ('do not look for one'). This is exemplary when/not-when guidance.

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