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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is known; the description adds real value on top by disclosing the return contents, the offline/unfiscalised flagging, and that open shifts are surfaced. It stops short of noting cost, latency, or how much history it can cover, so not 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?

Front-loaded with the resource and date scope, then contents, then caveats, then exclusions — a clean information gradient. Every clause carries either a return-value fact, a trigger phrase, or a boundary; none is 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?

There is no output schema, so the description must carry the return shape, and it does so field by field while also covering edge signals (unfiscalised receipts, open shifts). Combined with annotations covering the safety profile and a fully documented 4-parameter schema, nothing an agent needs in order to call it correctly is missing.

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 defaults and formats for point/since/until/by_day are already documented. The description still adds meaning by tying the outputs to the parameters — the 'broken down per sales point and per day' sections are what point and by_day control — giving the agent a reason to set them rather than just a type signature.

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 ('till takings over a date range') and then enumerates exactly what the report contains: total revenue, receipt count, average basket, cash/card split, millilitres sold, plus per-sales-point and per-day breakdowns. It also names what it does not do (opening/closing a shift, voiding a receipt), which lets an agent rule out fiscal-act tools without inspecting them.

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 concrete trigger questions ('how much did we take today / this week', 'which shop is behind', 'is anything unfiscalised') that map directly onto invocation decisions. It adds an explicit exclusion boundary — shift open/close and receipt voiding 'are not available here' — so the agent knows when to look elsewhere.

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