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

Annotations already declare readOnly, idempotent, non-destructive behavior. The description adds genuinely new context: the retroactive start-today-and-deduct rule for already-born children and the fact that it returns a source and a link. It does not describe output detail or limits beyond that.

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 core action, then the birth-date conditional, then the return value. No wasted text, though the Swedish phrasing is dense.

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 nested 5-parameter tool with no output schema, the description covers the main behavior and return hint (source and link). It stops short of explaining how the 1–2 parent split and the andel parameter interact, leaving some gaps for a fairly complex planner.

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 60%, and the description mentions the schedule dimensions (dubbeldagar, sjukpenningnivå, lägstanivå), dates and amounts, aligning loosely with the nested parameters. It adds only marginal meaning over the schema and leaves the uncovered 40% undocumented.

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 names a specific verb and resource: proposing a distribution of the remaining 480 parental days between 1–2 parents, with schedule, dates and amounts. This is clearly distinct from siblings like calc_benefit or days_remaining, though it never names them explicitly.

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 the conditional 'if the child is already born, the plan starts today and used days are deducted', which implies when the tool applies, but it offers no explicit guidance on when to prefer it over calc_benefit or days_remaining.

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