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

Annotations already declare readOnly/idempotent/non-destructive, so the 'Läser bara, ändrar inget' clause is partly redundant. But the description adds genuine behavioral context beyond the annotations: result format (account number, name, balance in öre with debit positive, sum debit and credit) and the accounting rule that balance accounts count from inception while income accounts count from fiscal-year start.

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?

Purpose is front-loaded, followed by sibling disambiguation, return shape, and accounting semantics in a tight sequence. Every sentence carries information; no filler.

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?

There is no output schema, so the description must carry the return-value burden, and it does: it explains per-account fields, currency unit, sign convention, and totals. Combined with the calculation rules, an agent has everything needed to call and interpret the result.

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 100% and both parameters are fully documented by the schema, so the baseline is 3. The description only loosely touches parameters via 'per ett datum', adding no format or constraint detail beyond what the schema already states for orgnr and balansdag.

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 ('Visar saldobalansen per ett datum') and immediately distinguishes itself from three siblings by name (get_balance_sheet, get_income_statement, get_general_ledger). An agent can route correctly without opening any other 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?

Explicitly says what the tool is for ('saldon per konto') and names the exact alternatives with their selecting conditions: balance sheet, income statement, and transactions. Nothing is left to inference about when to choose this versus a sibling.

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