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

Annotations only provide readOnlyHint=false and destructiveHint=false; the description adds substantive behavioral detail beyond them: which updates file tax certificates, which do not, and explicitly that it writes no payslip and posts nothing to the ledger. This is exactly the kind of side-effect information an agent needs for a mutation tool.

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 description is four tight sentences: purpose first, then create/update semantics, then side-effect conditions, then explicit non-actions. Every sentence adds material information with no 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 complex 25-parameter tool with no required fields, no schema descriptions, and no output schema, the description is strong on behavior but incomplete on parameter semantics. It gives enough to decide create vs update and to understand major side effects, but not enough to correctly populate many of the less obvious fields.

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 0% for 25 parameters, so the description carries the burden. It adds real meaning for 'id' (omit vs pass) and groups many fields semantically ('contact and identity details', 'standing package'), but it does not explain most individual parameters, the packagekind enum including '$delete', or the employments nested structure. It partially compensates but leaves major gaps.

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+resource ('Create or update a payroll employee') and enumerates the domains of data it covers: name, number, contact and identity details, role, department, employments, and standing package. This clearly distinguishes it from read-only siblings like get_employee and list_employees.

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 gives explicit create/update branching: 'Omit id to create; pass an id to update that employee.' It also states the side-effect conditions for updates that end employment versus re-sent end dates or status changes. It does not name alternative tools, but the create/update conditions are precise.

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