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

With annotations present, the description adds real value beyond them: it explains the mirror voucher that gets posted, that the run is excluded from AGI, and that history is preserved via status → reversed. That reconciles the apparently destructive verb with destructiveHint=false, so no contradiction. It still omits what happens on a second call (idempotentHint=false) or if the run is already reversed.

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?

Dense and front-loaded: purpose first, then side effects, then history semantics, then prerequisite. The trailing 'Argument: orgnr, run_id' adds no information and is the one redundant fragment.

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?

No output schema exists, yet the description covers the meaningful outcomes (mirror voucher, AGI exclusion, preserved history) and the auth scope. The main gap is the unresolved run_id parameter and undefined behavior on repeat/already-reversed runs, which is minor for a two-parameter operation.

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 only 50% – run_id has no description at all – so the description must compensate, and it does not: 'Argument: orgnr, run_id' merely restates the parameter names. It never explains what run_id refers to or that it comes from list_payroll_runs, which the sibling list_payroll_runs would supply.

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 ('Backa en bokförd lönekörning') and immediately scopes it to booked runs, which separates it from run_payroll (create) and list_payroll_runs (read). An agent can identify the operation 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 gives a clear precondition ('bokförd' – only booked runs can be reversed) and a hard requirement ('Kräver scope payroll'), which tells the agent when the call is valid. It does not, however, name an alternative or state what to do instead when the run is not booked, so exclusions are left implicit.

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