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

Annotations already declare readOnly, idempotent, non-destructive, which the description reinforces. It adds valuable behavioral context: 'Every output bound is non-zero and every step through the vault or the Zap carries its gas limit' and 'in the order to send them.' It also clarifies that nothing is signed or sent, which is a non-obvious behavior for a 'prepare' tool. No contradiction with annotations.

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 dense but efficient: it opens with the purpose, enumerates each action with its amount semantics in a compact list, and finishes with essential behavioral notes. Every sentence earns its place, and the information is front-loaded. No fluff.

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 an output schema exists (not shown but noted), the description doesn't need to detail return values. It covers the workflow (preview, prepare, send), the actions, amount meanings, gas limits, and ordering. It doesn't mention prerequisites like wallet balance or approvals, but those are likely outside the tool's responsibility. Overall, it is sufficiently complete for an agent to call it correctly.

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?

While the schema provides 100% coverage of parameters, the description adds critical action-specific meaning for the 'amount' parameter (e.g., 'amount in ETH' for mint_with_eth, 'amount = the USDC you need' for exit_to_usdc) and explains the optional 'row' default for bid. This is exactly the kind of contextualization the schema alone cannot convey, and it prevents misuse.

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 clearly states the tool builds unsigned transactions for vault operations, names the exact actions it supports, and distinguishes itself from siblings like actions.preview and payments.prepare by specifying the vault context and the non-execution nature ('Nothing is signed or sent'). It goes beyond a generic phrase and gives concrete scope.

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?

It explicitly advises the workflow: 'simulate the steps with preview_steps, then send them from the wallet.' This tells the agent when to use this tool relative to preview. It also clarifies that it is for vault operations and lists the supported actions, implying it's the preparation step for those. It does not explicitly contrast with payments.prepare, but the vault-specific actions make the distinction clear enough.

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