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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description goes beyond them by disclosing ordering ('most recent first'), pagination, the exact returned fields, and that all amounts are USD — meaningful behavioral context an agent cannot get from the annotations 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?

Three compact sentences, front-loaded with purpose and filters before ordering and return shape. Every sentence carries information: filters, sort order, pagination, field list, currency — no padding.

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 and four optional params, the description fully compensates by enumerating the returned fields (id, period, sub_total, vat, total, currency, status) and pagination meta, plus the USD currency caveat. An agent has everything needed to call and interpret it.

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%: page, year, month, and page_size all carry descriptions with defaults and ranges. The description's mention of year/month filtering restates the schema rather than adding syntax or edge-case detail (e.g. whether month requires year), 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 (List) and resource (the authenticated customer's invoices) with the available filters named up front. It is immediately distinguishable from get_invoice in practice, but the description never explicitly contrasts itself with the single-invoice sibling or other list_* billing tools, so it stops short of a 5.

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 conveys when the filters apply ('optionally filtered by year and/or month') and how results come back, which implies the browse-the-billing-history use case. However, it never says when to reach for this instead of get_invoice, list_payments, or list_refunds, and gives no exclusions or prerequisites.

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