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

Goes well past the annotations: it discloses that the call creates only a queued pending change, that a human must approve before Xero is touched, that the agent cannot self-approve, that the resulting record is a Xero-side DRAFT (unlike post_xero_pay_run), and that invalid earnings-rate/calendar combinations fail only at approval time. Annotation hints (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false) are consistent and the description adds the missing causal detail.

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-loads the most important fact (draft, human approval required, Xero untouched) and every sentence carries operational content. It is long and single-block, and repeats the NZ/UK whole-calendar-period rule that already appears twice in the schema, which costs some readability.

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 6-param, no-output-schema mutation tool it covers the approval lifecycle, return field (approvalUrl), region branches and known live-observed quirks well. However, the schema says to 'Follow the DATES instruction in this tool's description' for ambiguous numeric dates, and no such instruction exists here — leaving a real ambiguity-handling gap.

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; the description still adds cross-parameter logic — region-dependent selection of earningsRateId, reusing the same employee's ordinaryEarningsRateId for AU, and the whole-payroll-period rule for NZ/UK dates. Much of this duplicates the schema's own field descriptions, so it is additive but not uniquely informative.

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 ('Proposes a DRAFT timesheet for one employee/period') plus the supported regions and the explicit scope limit ('does NOT touch Xero itself'). It also distances itself from the sibling post_xero_pay_run, so an agent can tell the two apart without opening either schema.

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 clear prerequisites and ordering: employeeId and payrollCalendarId must come from list_xero_payroll_employees (same employee), and NZ/UK require list_xero_payroll_earnings_rates first. It also names the human-approval path (approvalUrl, approve_xero_pending_change context) and contrasts behaviour with post_xero_pay_run. It stops short of an explicit 'do not use this when...' exclusion, but the routing guidance is otherwise concrete.

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