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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description goes well beyond them by disclosing a non-obvious behavioral trap: `totals` and `dailyTrend` cover the WHOLE date range rather than the returned page, so the agent must quote them rather than sum rows. That is exactly the kind of guidance annotations cannot express.

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?

Front-loaded with the core identity in the first clause, then intent examples, then the pagination/totals caveat, then the sibling routing rule. Every sentence carries a distinct, actionable payload with no filler.

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 compensates by naming the reply's key fields (`totals`, `dailyTrend`) and explaining their scope, plus the row-per-order/refund shape. For a paginated reporting tool this is complete enough for an agent to call it and interpret the result correctly.

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 seven parameters (page, pageSize, outlets, stations, timezone, start/end) are already documented in the schema with defaults and formats. The description adds no parameter-level syntax or constraints beyond that, so the 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?

States a specific verb and resource ('order-by-order breakdown for a date range') plus the exact row granularity ('one row per order AND per refund'), which is the key distinguishing detail versus aggregate siblings. It also anchors the tool to a known UI surface (Reports → Sales Breakdown), so an agent can map user intent directly.

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?

Gives explicit user-intent examples ('show me the orders from Saturday', 'how many refunds last month') and names the alternative with the condition that selects it: 'For headline figures alone use get_financial_summary; this tool is for when the merchant wants to see the actual orders.' When-to-use and when-not are both present.

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