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

Beyond the annotations (readOnly/openWorld/non-idempotent/non-destructive), it discloses that it never signs or submits, that preparation does not authorize execution, that shares are checked against the vault's previewDeposit and refused past a pinned tolerance, and that every envelope is valid for 300 seconds before the verifier refuses it. That is rich operational context the annotations alone cannot convey.

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?

Purpose and the core commitment/tolerance constraints are front-loaded, and nearly every sentence carries a distinct constraint. It is a dense single block with several long clauses, so it loses a little on scannability but wastes little.

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 complex 6-parameter mutation-preparation tool, it covers the essential safety story: registry sourcing, commitment freshness, previewDeposit tolerance, non-authorization, non-submission, and envelope expiry. An output schema exists, so return values need not be restated.

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?

At 50% schema coverage, the description compensates by explaining that executableMarketId must name a registry row (not a vault) and that registryCommitment must equal the commitment recomputed over the current record or the row is refused as stale/foreign. It also clarifies the receiver is the signing account (relating to accountProfile) and refers to the pinned slippage tolerance, though slippage.maxBps and client_ref remain undocumented.

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+resource: it prepares the exact otto_prepare_swap envelope+prepareInput pair that deposits USDC into an executable Morpho vault on Base, with the vault's ERC-4626 share token as output. It explicitly differentiates itself from otto_prepare_swap (same pair shape), the withdraw counterpart, and the retired delegation path, so an agent can tell the siblings apart.

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?

Clearly scopes use to vaults pulled from the Yield Copilot registry rows and notes that otto_submit_under_delegation refuses this pair, which steers the agent away from the execution path. It does not explicitly state when to prefer this over otto_prepare_swap or otto_prepare_yield_withdraw, so the exclusions are implied rather than fully enumerated.

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