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

Beyond the annotation hints, it discloses where the artifact lands (file store, in the business's look and document language), the email side effect and its guardrails (sent in the business's name, subject to the standard bot email rules, at most once per customer per day), and the cost model ($0.05 per call, free on failure). This is exactly the kind of non-obvious behavioral context that annotations cannot convey, and it is consistent with readOnlyHint=false / openWorldHint=true.

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?

Almost every clause carries real information, but it is delivered as two very long run-on sentences where mode definitions, defaults, output location, email rules and pricing are all run together. The key distinction (outstanding vs activity) is buried mid-sentence rather than front-loaded, making it harder to parse than it needs to be.

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 10-parameter, nested-object tool with no output schema, the description covers the important ground: modes, defaults, artifact location, email behavior and pricing. What it never states is what the call actually returns to the caller (a file URL? an id? a status?), which matters when there is no output schema to fall back on.

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 70% schema coverage, the description still adds substantial meaning: it explains the two values of 'kind' in detail, supplies defaults for as_of ('today'), to ('this month so far') and currency ('the one they are billed in most'), and describes what 'from' anchors. Gaps remain for 'link_hours' and 'send_to', which are never mentioned despite link_hours having no schema description.

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 exact artifact ('A customer statement, like Xero's') and enumerates what it contains for both the 'outstanding' and 'activity' variants, so an agent knows precisely what it produces. It stops short of contrasting itself with sibling tools like invoices_report or invoices_summary, which a top score would require.

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 explains when each mode applies: 'outstanding (the default)' gives a point-in-time debt view as of a date, while 'activity' gives a from/to transaction history with a running balance. Defaults for kind, as_of, to and currency are spelled out. No explicit exclusions or named alternatives ('use invoices_report when...') are given, so it falls short of a 5.

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