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

Annotations only declare it a non-readonly, non-destructive, non-idempotent write. The description adds the crucial non-obvious behavior: it is a queued draft that books nothing ('Bieffekt: inget bokförs'), a human gate sits between proposal and booking, and it requires the 'reconcile' permission. It also documents the return fields (draft_id, serie, datum, status pending), all beyond structured data.

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 purpose, then usage, alternatives, return values, side effect, follow-up tools, and finally the FX edge case — a logical progression. It is dense and long, but nearly every sentence carries distinct information; only the FX paragraph could be trimmed slightly.

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 an 11-parameter mutation with no output schema and near-zero schema documentation, the description covers return values, approval workflow, permissions, side effects, and the FX edge case. The remaining gap is the shape of 'lines', which an agent must infer to actually construct a valid proposal.

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 9%, so the description must carry parameter meaning, and it does so for the hardest ones: it explains currency, foreign_amount_minor, fx_rate and total_sek_ore and how to derive SEK lines ('räkna raderna i SEK'). It leaves the required lines/text/date and series/note/underlag_ids structure unexplained, so coverage is substantial but incomplete.

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 ('Lägger ett verifikatförslag i kön Väntande verifikat') and pins down the scope: a human approves/rejects before anything is booked. It also names the sibling tools it is not (book_voucher, create_voucher, create_proposal), so an agent can distinguish it without opening any 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 an explicit trigger ('Använd när användaren vill granska först eller när konteringen är osäker') plus conditional alternatives: direct booking goes to book_voucher/create_voucher, and reconciliation adjustments go to create_proposal. It also names the downstream approve/edit/reject tools, leaving nothing to inference.

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