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

With no annotations, the description carries the full burden. It clearly states that deposit and withdraw return calldata (suggesting a non-executing, costless operation), and balance is read-only. It also discloses safety properties (no owner, no admin functions, NAV monotonicity, bytecode guarantees). However, it does not specify whether the calldata requires separate execution or signing, leaving some ambiguity.

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 a single, well-organized paragraph that introduces the tool, then lists each action on a new line with brief but complete explanations. Every sentence adds value, and the safety note at the end is relevant and succinct.

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?

Given the lack of output schema and annotations, the description covers the core functionality and safety properties fairly well. It omits details like exact return structure (e.g., whether calldata is hex-encoded), error conditions, and chain/contract address, but these may be considered secondary for an AI agent with appropriate schema context.

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?

The schema covers 67% of parameters with descriptions. The description adds crucial context: for deposit, it returns both approve and deposit calldata; for withdraw, just redeem calldata; for balance, it returns LOVE balance, NAV, and unrealized profit. This enriches understanding beyond the schema alone.

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 specifies the exact operations (deposit, withdraw, balance) and the resources (USDC, LOVE) with clear directional flow (USDC→LOVE, LOVE→USDC). It distinctly covers all three actions and sets this tool apart from siblings like nav_query.

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 lists the three actions and implies their usage contexts, but does not provide explicit guidance on when to use vault_action versus alternatives like nav_query or zhenghe_route. There is no exclusion criteria or explicit 'when not to use' statement.

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