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

Annotations already declare read-only, idempotent, non-destructive and open-world, so safety is covered. The description goes further with a real cost model: 1 call per 200 sales, cap of 10000 sales per range, parallel fetching, doubling by compareToPrevious, cached location/category lookups, and 1 call per 20 topClients (max 104). It also defines currency and the netSales/collected distinction, which are behavioral facts not present in annotations.

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?

Purpose and the get_sales routing rule are front-loaded, and the metric definitions and call-cost math are compressed into single clauses with no filler. It is a dense wall of text rather than structured into bullet-like segments, which slightly hurts scanability for a description this feature-rich, but no sentence is expendable.

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 9 parameters, the description carries the return-value burden and does so by enumerating every metric and breakdown section plus currency and netSales/collected definitions. The remaining gap is that it does not describe the response's overall shape (e.g. how totals nest relative to breakdown arrays) with 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?

Schema coverage is 100%, so the baseline is 3, but the description adds interpretation the schema lacks: what compareToPrevious does to call volume and how it aligns periods, that locations accepts names or IDs where get_sales cannot, and what netSales versus collected actually mean. The only gap is that it doesn't tie the top-N folding or interval auto-selection back to parameters, though the schema already documents those.

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 ('answers revenue and sales questions', 'reads every sale in a date range') and enumerates exactly what comes back: totals, byPeriod, topItems, byCategory, byPaymentMethod, byLocation, optional topClients and comparison. It explicitly distinguishes itself from get_sales by returning 'a compact summary instead of raw sales' and by supporting location filters get_sales cannot.

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 an explicit routing rule: 'Use this instead of get_sales for any "how much did we sell or make" question', with the inverse implied (get_sales for raw line items). It also flags the capability gap (location name/ID filtering) that makes this the only option for that case, so the agent has both a positive and a negative selector.

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