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

Goes well beyond the annotations by disclosing the payment workflow: the human always pays, the agent must never attempt payment or solicit card details, and the email is the delivery channel for the QR code. Combined with 'creates a real order,' this conveys the non-idempotent, consequential nature of the call.

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?

Four short sentences, each carrying a distinct instruction: what it does, who pays, what to collect first, and when it is safe to call. No filler; the outcome (payment link) is front-loaded.

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?

Despite having no output schema, the description names the return value (a payment link) and covers the prerequisites, safety constraints, and sequencing an agent needs to invoke a money-adjacent creation tool 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 coverage is 100%, so parameters are already documented; the description's email explanation largely echoes the schema. It does add workflow meaning by framing email as something to request from the user before calling, rather than a passive field.

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 specific verb+resource ('Create an unpaid eSIM order') and names the concrete artifact returned ('get a payment link'). This clearly distinguishes it from siblings like list_plans and order_status, which do not create anything.

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?

Provides an explicit precondition — 'call it only after the user picked the plan' — which implies the list_plans sequencing without naming the sibling directly. It also instructs to collect the email first, but does not explicitly route to any alternative tool or state when not to use it.

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