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, and the description still adds real value: it discloses that rendering and delivery are out of scope while the underlying content is in scope, preventing an agent from expecting a send action. It also flags the balance-forward structure, which tells the agent the output reconciles opening-to-closing rather than being a flat transaction dump.

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?

Two dense sentences, front-loaded with scope (one customer, period-bounded) followed by the exact output contents, then the structural framing and the scope exclusion. No filler, no restatement of the title.

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, and the description compensates well by enumerating the return sections in order, which is more than most tool definitions at this tier offer. Gaps are minor: no mention of behavior for customers with no activity in the period, and no indication of size or pagination for a statement covering a long window.

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 three parameters (customer_id, from, to) are already documented with types and ISO date format. The description reinforces the key semantic — the period is bounded and scoped to exactly one customer — and the balance-forward framing implies the opening balance is derived as of `from` rather than passed in, but no additional parameter guidance is given beyond that. Baseline 3 is appropriate.

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?

Names a specific resource (customer statement) and enumerates exactly what it contains: opening balance, invoices, credits, payments, refunds, closing balance, scoped to one customer and a bounded period. An agent can tell this is a report, not a mutation. It does not, however, explicitly distinguish itself from near-siblings such as o2c_ar_aging or solo_statement, which an agent could plausibly reach for instead.

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?

"Balance-forward style — the document a controller sends monthly" implies the consumption scenario (a periodic customer-facing statement) and the exclusion clause tells the agent it will not send anything. But there is no explicit when-to-use versus o2c_ar_aging (aging summary) or solo_statement, and no stated prerequisite such as the customer having posted activity in the period.

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