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

The annotations establish that this is a non-read-only, non-idempotent, non-destructive, closed-world write, and the description adds genuinely new behavioral facts: the return payload shape, that the bearer token is shown exactly once, that it only activates once paid, and that it must go into the operator's secret store. These are real consequences an agent could not infer from the schema. It does not address what happens on repeat calls (the non-idempotent hint implies duplicate invoices) or any expiry of the unpaid invoice.

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?

Two tight sentences, with the core action and return values front-loaded and the safety constraint and secret-handling obligation following. Every clause carries operational weight; there is no restated schema or filler.

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?

An output schema exists, so the description does not need to enumerate return fields, yet it highlights the two that matter for a payment flow. For a 2-parameter, high-consequence spend tool, it covers approval gating and secret handling, which are exactly the risk points an agent needs before invoking.

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% and both parameters carry their own descriptions (plan: pro/team/seller; network: tron/solana/ethereum), so the baseline is 3. The description adds only indirect meaning, that the chosen plan determines the exact USDT amount, without saying anything about network-specific addressing or how pay_to varies by network.

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 states a specific verb and resource ("Create an invoice") and immediately names the concrete payload: pay_to, the exact USDT amount, and a one-time bearer token. That is far more than a restatement of the title, and the payment semantics distinguish it from read-only siblings like invoice_status. It stops short of naming invoice_status as the follow-up or list_plans as the way to choose a plan, so sibling differentiation is implied rather than explicit.

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?

"Only call when your operator approved the spend" is a clear, actionable precondition that excludes speculative calls, and the token storage instruction gives the agent a post-call obligation. What is missing is routing guidance: the sibling list_plans exists and plan is a required enum-like string, yet the description never says to enumerate plans first, nor does it point to invoice_status for checking payment.

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