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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial behavior beyond them: the output structure (components, entry_ids, absence, notes), the side effect of marking hours paid when fed downstream, and the explicit guardrail 'Räkna aldrig om beloppen själv'.

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-loaded with the core scope before diving into output structure and workflow, and every sentence carries actionable content. It is dense and slightly long, but nothing is redundant.

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?

With no output schema, the description carries the return-value burden and does so by naming components, entry_ids, absence, and notes. Combined with the workflow guidance, an agent has everything needed to call and act on this tool.

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 50%: orgnr is documented in the schema, but through has no schema description. The description compensates by specifying through's format (YYYY-MM-DD) and default (today), adding meaning the schema omits.

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: approved but not-yet-paid hours per employee up to a date (attesterade, ännu inte utbetalda timmar per anställd t.o.m. ett datum). This precisely distinguishes it from siblings like get_time_reporting, list_time_entries, and get_payslip by scoping to the payroll-preparation view.

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 downstream routing: send components and time_entry_ids = entry_ids to calc_payroll/run_payroll to mark hours as paid, and flags that absence and notes must be handled manually. Strong context, though it does not explicitly contrast against the other time/payroll query tools an agent might pick.

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