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

Annotations only give the bare write/non-idempotent/not-destructive profile; the description goes well beyond by disclosing the exact ledger postings (D likvidkonto / K 1513), the denial fallback posting (D 1510 / K 1513), the side effect that the invoice becomes partially paid, and the auth/ceiling constraints. This is rich behavioral context an agent cannot get from the annotations.

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?

Front-loaded with the purpose, followed by posting logic, edge-case rules, prerequisites, then a compact argument summary. Dense but every sentence carries business meaning; the single-paragraph form is slightly harder to scan than a structured breakdown but not wasteful.

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 non-idempotent posting tool with no output schema, the description covers the accounting mechanics, denial handling, omitted-case default, required scope and ceiling constraint. It is light on error behavior when the ceiling is exceeded and on exactly how request_id maps to the source request, but the operational picture is otherwise 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%, so the description must compensate, and it largely does: it spells out the approved array shape as [{item_id, approved_ore}] with the semantic that the difference goes to the customer claim, gives pay_date format YYYY-MM-DD, and notes bank_account defaults to 1930. It leaves request_id's provenance (which request id) and item_id's source unexplained, keeping it from a 5.

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+resource in Swedish: registering Skatteverket's payout for a ROT/RUT request, and immediately disambiguates from next-step siblings like create_rot_rut_request, mark_rot_rut_request_submitted and reverse_rot_rut_payout by naming the payout event itself. An agent can distinguish it from those without opening the schema.

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 clear trigger context: use it when Skatteverket has paid out, and describes the partial/full denial branch plus the rule that omitted cases count as fully approved. It also states the 'scope book' prerequisite and bookkeeping-ceiling constraint. It does not explicitly name reverse_rot_rut_payout as the undo path or state when not to call it, so it falls short of a 5.

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