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

The description adds substantial behavioral context beyond the readOnlyHint annotation: nothing is prepared or sent, the call is free and changes nothing, and it explicitly warns that any argument is refused with VALIDATION_ERROR. These details are exactly what an agent needs to know before invoking a read-only report.

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 main purpose and is information-dense, but the single long paragraph is somewhat run-on and could be easier to scan. It remains efficient for the amount of return-shape and cadence detail it must convey.

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?

There is no output schema, so the description carries the full return-value burden and does so thoroughly: it defines reminders fields, issues drafts with next call, and recurring_held failures. It also explains time-zone scoping and side-effect behavior, leaving no major ambiguity for invoking or interpreting the tool.

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?

With zero input parameters, the schema already establishes the baseline, but the description reinforces it by stating 'it takes none' and that any argument is refused with VALIDATION_ERROR. That is useful negative-parameter guidance beyond an empty schema.

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 gives a specific verb-and-resource framing: 'Today's collection list' for invoices due reminders. It distinguishes the tool from generic invoice listing by defining the reminder cadence and the three returned sections (reminders, issues, recurring_held).

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 clearly establishes when the tool is used: today's collection list, with each invoice appearing only on its own reminder day and per client cadence. It also names related calls for setting cadence (invoice_client_update), preparing messages (invoice_message_prepare), and issuing drafts (invoice_update), though it does not explicitly compare itself to sibling list tools like invoice_list or sales_receivables.

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