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

Annotations declare non-read-only, idempotent, non-destructive, and the description's mutation semantics agree with that. It adds genuine context beyond the annotations: the exact state transition, the attestation gate, and the required 'reconcile' permission.

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 tight sentences with no filler; the change in state and the blocking condition are front-loaded before the permission and argument list. Appropriate length for the operation's complexity.

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 no-output-schema mutation tool the gating and permission details are well covered, but with 20% schema coverage the four undocumented parameters leave an agent guessing about accepted formats and values. Adequate, not complete.

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 description coverage is only 20% (only orgnr is documented), so the description carries the burden — but it merely enumerates the argument names already visible in the schema. It adds no format, range, or valid-value meaning for year, month, account, or bilaga_type.

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 ('Ångra') and resource ('FÖRBEREDD-markering på en bilaga') and spells out the state effect (tar bort PREPARER-steget, status → Ej startad). It is the clear inverse of the sibling prepare_bilaga, though that sibling is not named 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?

Gives real usage conditions: it is refused if the bilaga is already attesterad, in which case a human must undo the attestation in the app first, and it requires the 'reconcile' permission. It stops short of naming alternative tools, but the operative when/when-not is present.

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