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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=false; the description adds genuinely new behavior: the action is internal-only and reversible ('eller ångrar'), it sits in statutory scope, and the agent must confirm with the user before doing it. It doesn't explain what downstream state is affected (statutory status, year-end checklist), so it stops short of a 5.

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?

Four short, front-loaded clauses with zero filler; the confirmation warning and the internal-only note come early. The trailing 'Argument: orgnr, year; valfritt signed (default true)' repeats schema content and is the only soft redundancy.

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 3-parameter mutation with no output schema, the description covers intent, safety (confirm first), reversibility and scope, which is solid. It omits prerequisites (must the fiscal year be locked? must bilaga/steps be complete?) and any relationship to read_statutory_status or get_arsredovisning_status, leaving an agent unsure of the preconditions.

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 33% (only orgnr is documented), so the description carries extra burden. It clarifies that signed is optional and defaults to true — the undo path — which adds real meaning, but 'year' is left undefined (fiscal year id vs. calendar year) and 'orgnr, year' merely restates the schema keys.

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: marking the årsbokslut as prepared and signed, with an undo option (signed=false). It also distinguishes itself conceptually from submission siblings by clarifying 'Internt; årsbokslutet lämnas inte in någonstans' — i.e., unlike mark_submitted/mark_ink4_submitted, nothing is filed externally. It does not name the alternative sibling explicitly, keeping it just below a 5.

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 a concrete operational rule — 'Bekräfta med användaren först' — plus context that this is a statutory-scope action. It implies when to use it (once the årsbokslut is actually signed) but never states when NOT to use it or which sibling to prefer when a real submission is intended.

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