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

Beyond the annotations, the description discloses a non-obvious global side effect: changes affect all future invoices and offers but not existing ones. It also states that certain fields remain unchangeable even with approval and gives a policy for out-of-scope requests. These are valuable behavioral details that annotations alone do not convey, and there is no contradiction with 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?

Three short, deliberately separated paragraphs: purpose and effect, immutable exclusions, and the viewing prerequisite. The content is front-loaded and every sentence carries operational weight, including the Meistron referral. The emphasis and list of exclusions are justified rather than 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?

For a mutating settings tool, the description covers scope, immutability boundaries, handling of forbidden requests, and the necessary viewing pre-step. The idempotency protocol is already fully detailed in the input schema, so its absence from the description is not a gap. An agent has enough information to invoke the tool correctly.

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 the schema already thoroughly documents feld, wert, and idempotency_key. The description does not add new parameter-level meaning beyond framing settings as company/invoice defaults and pointing to 'einstellungen_ansehen', which the schema already mentions. Baseline 3 is appropriate.

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?

The opening sentence names the verb ('Ändert') and the resource ('Firmen- oder Rechnungsvorgabe'), then narrows the scope further: 'Wirkt auf ALLE künftigen Rechnungen und Angebote, nicht auf bestehende.' This clearly distinguishes the tool from 'einstellungen_ansehen' and gives an agent a precise mental model of what it does.

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?

The description gives a concrete prerequisite and sequence: call 'einstellungen_ansehen' first to know today's value. It also defines when not to act by listing immutable fields and instructing agents to refer to Meistron for those requests. It stops short of framing this as an explicit 'use this instead of X' decision against an alternative tool.

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