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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds substantive behavior: unsigned-and-unbroadcast output, step ordering, non-zero output bounds, per-step gas limits through vault and Zap, redeem having no fee and no price feed, and exit_to_eth being all-or-nothing. This is exactly the domain context annotations cannot carry.

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 core purpose, then a dense but necessary per-action parenthetical covering all seven enum values, closing with the signing/return behavior. Efficient for the scope, though the single run-on block with embedded parentheticals is harder to scan than a short list would be.

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 4-param tool with a full output schema, the description covers action units, bid defaults, and the unsigned output contract, so an agent can call it correctly. The remaining gap is the sibling relationship to actions.preview/status and the surrounding sign-and-relay workflow, which is 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 coverage is 100% (baseline 3), but the schema explicitly defers to the description for the amount unit ('see the description'), and the description supplies per-action unit semantics (ETH/WETH/USDC/shares) plus 'amount = the USDC needed' and the row default for bid. It adds genuinely necessary meaning beyond the structured field definitions.

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 precise verb and resource ('Builds the unsigned transactions for an operation on the GBLIN vault') and then enumerates every supported action with its unit and routing (mint_with_usdc through the Zap, bid against the rebalancing auction, etc.). An agent can tell what this tool does and which operation each enum value represents 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?

Usage is implied rather than stated: 'Nothing is signed or sent: the steps are returned to the caller' hints that this is a build step preceding signing, but the description never names when to choose it over siblings such as actions.preview, actions.status, or payments.relay, and gives no prerequisites or exclusions.

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