Wave: List Invoices

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds value by clarifying status semantics (UNPAID vs OVERDUE), which is a behavioral nuance beyond the raw schema. However, it does not disclose pagination behavior, return format, or that results are a list (though the name implies it). With annotations carrying the safety burden, the description adds modest behavioral context, warranting a 3.

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 two sentences with zero waste. The core purpose ('List invoices...') is front-loaded, followed by a concise, high-value elaboration on the most common use case (unpaid vs overdue). Every word earns its place; no redundant or filler text.

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?

Given the tool has 15 parameters, no output schema, and annotations covering read-only safety, the description focuses on the most pivotal filtering scenario (unpaid vs overdue invoices) which is the primary reason an agent would call this tool. It does not mention pagination or response_format, but those are documented in the schema. For a list tool with rich schema and annotations, the description addresses the key decision point sufficiently. A 5 would require explicating pagination or return structure, but the schema mitigates that gap.

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 100%, so all 15 parameters are already documented. The description adds meaningful semantics specifically for the status parameter, explaining the difference between UNPAID and OVERDUE in the context of finding unpaid invoices—information not in the schema. This extra guidance elevates it above the baseline 3 for fully-covered schemas.

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 ('List') and resource ('invoices') with applicable filters (status, customer, date range, amount due). The verb distinguishes it from the sibling wave_get_invoice which retrieves a single invoice, and the filter list clearly signals this is a collection operation. The purpose is 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?

The description gives explicit, actionable guidance for the status parameter: 'To find unpaid invoices use status "UNPAID"; "OVERDUE" narrows that to ones past their due date.' This tells the agent exactly how to approach a common task. It does not explicitly state when to use this tool versus wave_get_invoice, but the verb distinction makes that implied. No exclusions or alternatives are mentioned, so it falls short of a perfect score.

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