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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses the actual side-effect conditions: an update that ends an employment by adding a new end date with no next-day employment files tax certificates, while a status change, re-sent end date or create files nothing. It also explicitly bounds scope by stating no payslip is written and nothing posts to the ledger. That is exactly the behavioral context an agent needs before mutating payroll data.

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?

Three sentences, front-loaded with the verb and the create/update rule, with the payroll side effects stated last. The middle sentence is clause-heavy ('a new end date with no employment starting the next day') but every detail is load-bearing for correct invocation, and there is 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?

This is a 25-parameter upsert with no required fields and no output schema, so the agent must infer what constitutes a minimally valid create or update. The description handles the side-effect semantics well but leaves a substantial gap on parameter-level requirements and dependencies (template ids, jurisdiction, employment status). Adequate to call safely at a high level, but not complete for a tool of this complexity.

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 only 20% out of 25 parameters, so the description carries more burden than usual. It does group the fields into recognizable categories and explains the id-based create/update switch, but it adds no meaning for the undocumented bulk of the schema — the employments array shape, status values, what a 'standing package' requires, or which fields matter for a valid create.

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 ('Create or update a payroll employee') and enumerates the covered data groups (name, number, contact, identity, role, department, employments, package). The create-vs-update rule keyed on 'id' makes the operation unambiguous. It doesn't explicitly contrast itself with nearby siblings such as save_client, save_supplier or get_employee, which keeps it at a 4.

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 a concrete decision rule: omit id to create, pass an id to update that employee. It also implies use is for creating or modifying employees rather than reading them. What it lacks is guidance on prerequisites (e.g. fetching an existing employee first, dependency on payroll setup or jurisdictions) and any explicit 'use X instead' routing.

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