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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds value beyond that: result ordering, the exact field set returned, the absence of date/customer filters, and a genuinely useful quirk that statuses are returned capitalized here but lowercase from get_invoice. Pagination behavior is only implied via the cursor parameter rather than described, which keeps it from a 5.

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?

Four dense sentences, front-loaded with what is returned and ordered before the filtering constraints, with no filler. The past-due workaround sentence is long but operationally necessary. Minor grammar awkwardness in "compare due_at with today where due_amount is above 0" slightly hurts scannability.

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 correctly compensates by listing the returned fields and their ordering. Combined with annotations and a fully documented schema, an agent has enough to call this correctly. The one remaining gap is that pagination (cursor/next_cursor) is never described in prose, though the schema covers 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%, so limit, cursor and status are already fully documented with enum values and defaults. The description restates the status enum and clarifies that unsupported filters do not exist, which is mildly useful, but adds no new syntax or semantics for limit or cursor. Baseline 3 applies when the schema carries the parameter burden.

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 names the resource and its ordering ("Invoices, newest number first") and enumerates the fields returned (customer, amount, amount due, last payment), which tells an agent exactly what it gets. It is clearly distinguishable from get_invoice, which is called out by name for a contrasting behavior. It stops short of a 5 only because the verb is elided into a noun phrase, leaving the action implicit from the title.

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 states a firm exclusion ("Filters by status only... there is no date or customer filter"), which prevents an agent from attempting unsupported filtering, and it gives a concrete workflow for past-due invoices (read open ones, compare due_at with today where due_amount > 0). It also routes to get_invoice for a related concern. No explicit statement of when this tool is preferred over list_customers or list_jobs, so not a 5.

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