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

Annotations only declare readOnlyHint=true; the description adds the crucial operational fact that the server performs no data or RPC request, so category IDs are caller-supplied and unverified against live chain state. That explains why the tool is read-only despite preparing a state-changing user action. It does not describe what the prepared payload looks like, though an output schema exists to cover that.

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 clauses with no filler, and the operative fact (caller supplies the category, server does no lookups) is front-loaded. The density makes it slightly hard to parse, but every phrase carries information.

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?

Annotations and a full-coverage schema plus an output schema cover most needs, and the description supplies the non-obvious constraint that live eMode configuration must be fetched elsewhere. What is missing is the downstream step: that the returned object is an unsigned transaction/calldata the caller must submit.

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%, so all three parameters are already documented in the schema, including the uint8 range, the zero-disables semantics, and the GraphQL sourcing of category IDs. The description restates the category_id constraints rather than adding meaning beyond them, 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?

Names the exact contract method (setUserEMode) and the resource it acts on, which unambiguously separates it from the many sibling prepare_aave_v3_* tools (supply, borrow, repay, collateral, withdraw). An agent can identify the operation without opening the 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 the key semantic rule (zero disables eMode) and tells the caller how to obtain nonzero category IDs, namely from Aave's public GraphQL API. It stops short of naming sibling alternatives (e.g. get_aave_v3_markets for chain selection) or stating that the result must be signed and broadcast by the caller.

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