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

With no annotations, the description carries full burden and excels: it discloses address preservation, trial-to-plan behavior, planless return of eligible plans, and idempotency ('Pressing it twice quotes the same reference rather than raising a second invoice'). This goes well beyond basic function.

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 front-loaded with the core action and then adds logically ordered details on trial, plan, and idempotency. Every sentence contributes; however, it is moderately long, so not a perfect 5.

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?

For a tool with no output schema or annotations, the description covers key behavior, edge cases, and idempotency, making it largely complete. It doesn't detail error conditions or return formats, but for this simplicity level it's adequate.

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 covers both parameters with helpful descriptions (e.g., plan defaults, access_token provenance). The description adds extra semantics: the plan behavior when omitted on a trial and the idempotency consideration, which are not in the schema. This justifies a score above the 3 baseline.

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 'Raise an invoice for another term and keep the same addresses' — a specific verb and resource that clearly distinguishes renewal from sibling tools like order_lease or lease_status. It also ties to the trial-to-paying transition, making the purpose unambiguous.

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 provides contextual guidance: 'This is how a trial becomes a paying customer' and explains when plan is needed and what happens if omitted. While it doesn't explicitly contrast with alternatives, the trial-to-payment scenario gives clear use case. Could be improved by naming when not to use, but overall strong.

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