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

Beyond the destructive annotation, the description discloses crucial behavior: confirm: true is required for send/email effects, omitting it yields a preview, paused dates are skipped, and invoice lines remain as copied. These details materially affect safe invocation.

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 and every clause carries semantic load, with no obvious filler. It is dense and could be more scannable, but it is appropriately sized for a complex mutation tool.

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 complex update tool with no output schema, it covers the critical invocation semantics: preview versus execution, pause/resume behavior, and field effects. Some details, such as exact preview output or action enum effects, rely on the schema or inference.

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?

The description adds meaning beyond the schema for nearly every parameter: nextDate resets the cadence, endAfter null means no end, active false/true pauses/resumes, confirm controls execution versus preview, and it maps the remaining fields to cadence, action, and payment terms.

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: it changes a recurring invoice and enumerates the aspects that can be changed. This clearly distinguishes it from sibling operations such as create_recurring_invoice, delete_recurring_invoice, and list_recurring_invoices.

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 gives clear usage context for pausing, resuming, and making changes that send or email new invoices, including the confirm requirement. It does not explicitly name sibling alternatives, but the update context is unambiguous.

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