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

Beyond the annotations, it discloses that nothing executes on this call, that execution is gated on a user opening the link and pressing Confirm in Netto, and that the link expires in 30 minutes. These are exactly the operational facts an agent cannot infer from destructiveHint/readOnlyHint alone.

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?

Short, front-loaded, and every sentence carries operational weight (deferred execution, expiry, prohibition on claiming success). Slight redundancy between 'Nothing happens yet' and 'the action only runs after they open it' keeps it from a 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?

With no output schema, the description steps in to describe the return value (a confirmUrl) and its lifetime, plus the interaction contract. That covers the critical unknowns for a destructive, open-world, non-idempotent operation.

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 invoiceId, customerName, and paidDate are already documented in the schema. The description adds no extra meaning about what customerName is used for or how paidDate feeds the confirmation, so the baseline 3 applies.

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 and resource ('Prepare marking one invoice as fully paid') and immediately clarifies the two-phase nature of the operation. An agent can tell this is not send_invoice or query_invoices because the deliverable is a confirmation link, not an immediate mutation.

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 instructs the agent to hand the confirmUrl to the user and to never claim the action was done — strong when-to/how-to guidance with a hard prohibition. It stops short of naming alternatives (e.g., when to use send_reminder instead for unpaid invoices), so 4 rather than 5.

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