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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety profile is covered. The description adds genuine value beyond that: it discloses the return content (per-asset debit/credit rows + amount, a total, and an already_posted flag) and the required 'view' permission, which the annotations do not convey.

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?

A single dense, front-loaded block: the core action and its non-posting nature come first, followed by return contents, scoping, permission, and arguments. No filler sentences.

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 4-param, no-output-schema tool, the description compensates well by describing the return shape (rows, total, already_posted), the auth requirement, and the scoping behavior. Minor gaps remain around period/validation semantics, but the essential calling information is present.

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 only 25% (only orgnr documented), so the description must compensate. It lists the arguments explicitly and clarifies that asset_id is optional and scopes the preview to one asset, adding semantics the bare integer schema omits. year/month remain self-evident but unexplained.

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 ('Förhandsgranska' = preview) and resource ('avskrivning' = depreciation), and immediately scopes it against the write counterpart with 'UTAN att bokföra' (without posting). An agent can distinguish this from the sibling post_depreciation 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?

Explains the key usage condition (preview only, no posting) and clarifies that supplying asset_id narrows the preview to a single asset. It also states the required permission ('view'). It does not explicitly name post_depreciation as the alternative when you actually want to commit, so it stops just short of full routing guidance.

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