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

Annotations already declare destructiveHint=true and idempotentHint=true, so the mutation profile is known. The description adds genuinely useful behavior the annotations cannot express: that nothing is actually filed externally and that user confirmation is required first. It still doesn't say what internal state changes or whether the flag can be inspected afterwards (e.g. via read_statutory_status).

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 sentences with the core action front-loaded, followed by scope clarification, the confirmation requirement, and parameter notes. No filler; the terse 'Argument:' listing earns its place given the low schema coverage.

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 three-parameter destructive mutation with no output schema and sparse schema descriptions, the description supplies the essentials: what is set, that it is internal-only, the confirmation gate, and the default for the optional flag. It could go one step further by naming how to verify the resulting status.

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% — orgnr is documented in the schema while year and submitted are bare. The description compensates partially by stating 'valfritt submitted (default true)', which confirms submitted is optional and toggles direction, but it says nothing about the accepted range/format of year beyond the orgnr schema 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?

The description names a specific verb and resource ('Markerar NE-bilagan som inlämnad ... för ett år') and even covers the inverse toggle ('eller inte inlämnad'). The resource is specific enough to separate it from siblings like mark_ink4_submitted or mark_rot_rut_request_submitted, though it never names those alternatives 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 clear situational context: this is an internal flag and no filing to Skatteverket occurs, plus an explicit workflow prerequisite ('Bekräfta med användaren först'). What it lacks is any exclusion or pointer to a sibling for the cases where this is the wrong tool.

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