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

With annotations already declaring idempotent=true, destructive=false and a write operation, the description still adds real value: it discloses that null clears the planned date and that the forecast counts the payment on the planned day even for an already-overdue bill, which would otherwise be excluded. That is behavioral context not present in the 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?

The core semantics and the cash-forecast consequence are front-loaded in the first clause, with the terse 'null clears it' and 'Free' trailing as useful asides. It is a dense run-on sentence, but almost every clause carries information; nothing 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?

For a two-parameter setter with full schema coverage and no output schema, the description covers the state being written, the null/clear case, and the observable business effect. The main omission is whether it returns anything or how it interacts with paying the bill.

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 baseline 3, but the description contributes the crucial semantic that date=null clears the planned date (the schema only says 'or null'), and that bill_id must reference an unpaid bill. This meaningfully reduces ambiguity about the clear operation.

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 defines the resource precisely — the intended payment day for an unpaid bill — and grounds it in a known analogue (Xero's planned date). It is clear what state it sets, though the imperative verb ('set') is only implied by the tool name rather than stated in the text.

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 scopes usage implicitly to bills that are 'not paid yet' and notes the downstream effect on books_report cash_forecast, which helps an agent see why to call it. But it never names alternatives such as purchasing_pay_bill or invoices_set_expected_date, nor states exclusions (e.g., what happens if the bill is already paid).

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