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

Annotations already declare idempotentHint=true, so 'asking again returns the same Beleg' merely restates structured data. More importantly, destructiveHint=true and readOnlyHint=false signal a mutating, potentially destructive operation, yet the description never says what happens to the source attachment or answer (is the document moved, copied, or consumed?), nor what permissions or preconditions apply. With the annotation bar already flagging destruction, this is the exact context the description should supply and does not.

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 compact sentence with no filler, and the idempotency guarantee is appended right where it matters. However, the extreme brevity leaves the key mutation semantics unstated, so terseness here trades off against completeness.

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?

An output schema exists, so return values need not be explained, and both parameters are fully documented in the schema. Still, for a destructive, open-world mutation tool with a named conversion side effect, the description omits what changes in the system and under what conditions the call fails, leaving the agent under-informed relative to the tool's risk profile.

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% with only two well-described parameters, so the schema carries the burden. The description does add a hint that attachment_id refers to a document inside an Aufgabe's answer, marginally reinforcing the schema wording, but no format, naming, or company-scoping detail beyond that.

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 target resource: converting a document attached to an 'answer' into a Beleg. The purpose is clear, but 'answer' is undefined in the description (presumably an Aufgabe's answer, only recoverable from the title and schema), and nothing distinguishes it from siblings like upload_beleg or link_beleg, which sound like they also create Beleg records.

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?

Usage is only implicitly conveyed: use it when a document sits in an answer and you want it to become a Beleg. There is no explanation of when to prefer upload_beleg, link_beleg, or attach_vertrag, nor any prerequisite about the Aufgabe/answer needing to exist or already be answered.

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