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

Annotations supply only readOnlyHint=true, so the description has to carry most of the behavioral burden, and it does add real context: underlying repayment bundles an exact ERC-20 approval plus cleanup into one atomic plan, which tells the agent about approval lifecycle side effects. It stops short of saying explicitly that the output is an unsigned plan rather than an executed transaction, or whether on_behalf_of requires authorization.

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?

Two tight sentences with the resource and funding modes front-loaded, followed by the atomic-approval consequence and the max-amount convention. Nothing is wasted and there is no repetition of the title.

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?

An output schema exists, so return values need not be described, and the six-parameter surface is fully documented in the schema. What is missing is small but real: the plan-vs-execution nature of a 'prepare' tool and the authorization expectations for on_behalf_of are left implicit.

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 asset, amount, sender, chain_id, on_behalf_of, and funding_source, which sets the baseline at 3. The description reinforces the max-uint256 convention and the underlying/aToken distinction but adds no syntax, constraints, or format detail beyond what the schema fields already say.

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 (prepare) plus the exact resource (Aave V3 variable-debt repayment) and the two funding modes (underlying ERC-20 or sender-owned aTokens). This clearly separates it from siblings such as prepare_aave_v3_borrow, prepare_aave_v3_supply, and prepare_aave_v3_withdraw without opening any 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?

The description implies when each funding path applies (underlying vs aToken) and notes that uint256 maximum requests all available debt, which is genuine usage guidance. It never states prerequisites or exclusions relative to other prepare_* tools, so an agent must infer that a market must first come from get_aave_v3_markets and that this tool only builds a plan rather than executing it.

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