mhlb_checkout

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

Annotations only indicate readOnly=false and openWorldHint=true. The description goes far beyond: it warns the write is UNVERIFIED, derived from compiled client, not exercised live. It explains the expectedTotal's role as attribution-only and the need to inspect dry-run before confirming. This is exemplary transparency for a risky write operation.

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 one dense paragraph that front-loads the purpose, then gives prerequisite, limitation, and caution. No filler; every sentence carries necessary information. It's appropriately concise for the tool's complexity.

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 9 parameters, no output schema, and a real-money write, the description covers all essential operational aspects: what it does, prerequisite, limitation, verification status, and confirmation workflow. The agent has enough to invoke it safely and 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?

Schema descriptions cover all 9 parameters, so the baseline is 3. The description adds critical context for expectedTotal—that the server prices from orderIds, so this value is recorded for attribution, not for validation—which is beyond the schema. It also reinforces the init_checkout flow. This elevates it to a 4.

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 opens with a specific verb and resource: 'PAY for the lunches in the cart.' It clearly distinguishes this from siblings like mhlb_init_checkout by stating it charges a real payment method. No ambiguity about the operation's goal.

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 instructs to run mhlb_init_checkout first, read the total, and pass it as expectedTotal. It also notes the hard limitation that only saved cards can be used, so agents know when this tool is not applicable. The dry-run preview instruction further guides when to confirm.

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