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

Annotations already declare a destructive, idempotent, non-open-world mutation; the description adds genuinely new behavior context: the change is an internal bookkeeping flag with no external submission, it can be reversed by setting submitted=false, and user confirmation is required. It does not say what downstream state (e.g. statutory status, checklist) is affected.

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 short sentences and a fragment, front-loaded with the action, then the scope caveat, then the confirmation rule, then the arguments. No padding; the terse 'Scope statutory. Argument: ...' style is efficient even if telegraphic.

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 destructive mutation with no output schema and thin schema coverage, the definition covers the critical safety points (internal only, confirm first, reversible). It leaves gaps on what 'year' refers to and what record the flag lands on relative to read_ink4 / read_statutory_status, which an agent would need to act confidently.

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?

With only 33% schema coverage, the description must compensate, and it does so only partly: 'valfritt submitted (default true)' plus 'eller inte inlämnad' conveys that the boolean toggles the flag in both directions, which is useful. However 'year' is never explained (calendar vs. fiscal year, format), and 'orgnr' is restated rather than enriched beyond the schema's own list_companies hint.

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 ('Markerar INK4 som inlämnad') plus the scope of the flag ('för ett år') and the negative case ('eller inte inlämnad'). It does not name the closest siblings (mark_submitted, mark_ne_submitted, set_ink4_inputs), so the agent must infer differentiation, but the operation itself is unambiguous.

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?

'Internt; ingen inlämning till Skatteverket sker' clearly bounds when this tool is appropriate and prevents confusion with an actual filing action. 'Bekräfta med användaren först' adds a concrete precondition. Missing is any explicit routing statement versus mark_submitted or set_ink4_inputs.

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