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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), it discloses the two-phase dry-run/confirm workflow and, critically, the blast radius: finalised payslips, closed periods and existing drafts keep their figures, and only payslips created or re-populated afterwards pick up the new settings. That retroactivity detail is exactly the kind of behavior an agent cannot infer from structured fields.

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?

Four tight sentences, front-loaded with what changes, then the call protocol, then the side-effect scope. No filler or redundancy; each sentence carries a distinct, decision-relevant fact.

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 zero-required-parameter mutation tool with nested objects and no output schema, the description covers the call sequence, side effects and where to get valid ids. It stops short of describing the shape of the approval response or any permission/entitlement requirements, which a caller might still wonder about.

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 the schema already explains confirm, the settings id-value map, null-to-reset behavior and the '$delete' jurisdiction sentinel. The description adds the partial-update convention ('Send only the settings to change') and the approval workflow around confirm, but mostly restates what the schema documents, so the baseline of 3 applies.

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 opens with a specific verb and resource ('Change this business's payroll settings, the country pack's settings and the jurisdiction') and names the sibling get_payroll_setup as the source of valid ids. An agent can distinguish this from save_employee, save_payslip or save_payslip_template without opening any 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?

It spells out the when and the when-not explicitly: the first call saves nothing and returns the proposed changes, and the second call is only made 'after the user approves them'. It also points to get_payroll_setup for enumerating setting ids and jurisdiction options, so the agent knows how to prepare the call.

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