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

With no annotations, the description carries the full burden and delivers: server-side policy limits, meaning of the three statuses (confirmed, confirmed_simulated, awaiting_approval), the warning never to present simulated payments as real, the next_action.url flow for pending payments, and the idempotency consequence that a new key spends again. This is a comprehensive behavioral contract for a money-moving tool.

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 long but every sentence earns its place: purpose, trigger conditions, policy constraint, status semantics, pending-state action, anti-double-payment rule, and idempotency usage. It is front-loaded with purpose and usage before behavioral details, and there is no filler or repetition.

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?

This is a high-stakes mutation tool with no output schema and no annotations. The description compensates by explaining exactly what the agent should do on each outcome (show next_action.url for awaiting_approval, never report confirmed_simulated as real, query get_payment when unsure). Nothing an agent needs to call this tool correctly is missing.

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 description coverage is 83%, above the 80% threshold, so the baseline is 3. The description adds genuine meaning beyond the schema for idempotency_key: reuse for retries of the same payment, while a new key 'means a genuinely new payment and will spend again' — a consequence the schema does not state. It does not add detail for other parameters, but the schema already covers them.

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+resource pair ('Create a payment intent') and expands the scope by enumerating realistic trigger cases: paywalled APIs, datasets, top-ups, other agents. It distinguishes itself from siblings by pointing the agent to get_payment/list_payments for status checks instead of creating a new payment.

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?

Explicitly states when to use ('Use this whenever completing your task requires paying someone') and when not to use it ('do not retry while it is pending', 'NEVER create a second payment because you are unsure the first worked'). It names the alternatives (get_payment or list_payments) for verifying outcome, leaving no ambiguity about routing.

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