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

Annotations already declare destructiveHint=true, idempotentHint=false and non-read-only, so the safety profile is covered. The description adds real context beyond that: it generates a number (MA-…) and stores a PDF in the archive, telling the agent what side effects to expect. It stops short of stating permissions or whether prior notices can be revoked.

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?

Two tight sentences, front-loaded with the core action and condition, followed by the concrete outputs. Nothing is wasted.

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?

With no output schema, the description carries return-value burden and does so adequately by noting the generated MA-… number and archived PDF. Combined with full param coverage and annotations, an agent has enough to call it correctly, though auth/irreversibility details are left implicit.

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%, so both id and level are documented in the schema (level empty = next level). The description reinforces the escalation concept but adds no syntax or format beyond what the schema provides, so 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: issuing the next dunning level for an overdue invoice, including the escalation concept (Zahlungserinnerung, then Mahnungen). The action is unambiguous. No sibling happens to overlap, so no differentiation is needed, but it also doesn't explicitly route against siblings.

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 clear triggering context: use it for an overdue invoice to escalate to the next dunning level, and describes the progression order. There are no obvious alternatives among siblings to exclude, so the lack of explicit exclusions is minor.

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