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

Goes well beyond the annotations by disclosing the overwrite side effect ('tidigare rader skrivs över'), that the attestation is untouched, the required permission ('Kräver behörigheten reconcile'), and the returned content. Since annotations already declare write/idempotent/non-destructive, this added behavioral context is a genuine gain; a possible tension with destructiveHint=false exists but the full-state 'set' semantics and idempotent re-run make it defensible rather than contradictory.

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-loads the purpose, then usage, then behavioral consequences and return values, in a compact single block. Dense but every sentence carries information; slightly more prose than strictly required but 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?

Although there is no output schema, the description states what is returned (rows, reconciled amount, difference), the destructive side effect, the permission requirement, and the relationship to get_reconciliation. Nothing essential for a correct call is missing.

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 100% and every parameter (orgnr, bilaga_type, account, year, month, rows) is already documented in the schema. The description adds conceptual meaning for rows (their sum becomes the reconciled amount, [] empties it), but no per-parameter syntax beyond what the schema supplies, so the baseline 3 applies.

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 ('Ersätter alla manuella specifikationsrader på en avstämning'), and immediately distinguishes itself from the sibling add_bilaga_row by naming the full-set-replace semantics. An agent can tell it apart from the incremental-row tool without opening either 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?

Explicit when-to-use ('när hela specifikationen ska sättas eller nollställas (skicka [] för att tömma)'), explicit when-not ('för att lägga till en enstaka rad och behålla resten'), and it names the alternative (add_bilaga_row). It further routes the agent to get_reconciliation for the gl_balance_ore needed to zero the difference.

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