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

Annotations already declare readOnly=false, destructive=false, idempotent=false, and closed-world. The description adds meaningful state context—this creates a draft, not a finalized credit, and prices remain editable afterward—without contradicting 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?

Two dense sentences front-load the resource and workflow; 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?

For a three-parameter draft-creation tool with no output schema and safety annotations, the description supplies the critical nested-object mapping and follow-up workflow. The unexplained reason parameter leaves a small gap.

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?

The nested quantities parameter is given precise semantics: keys are line-item IDs from get_document and values are returned quantities. The schema also documents id as Beleg-ID, but reason has no explanation in either place, so the low 33% coverage is only partly compensated.

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 description identifies the resource as a credit note (partial credit) and the operation as creating a draft tied to an issued invoice. It is specific enough to separate this from a full-invoice cancellation, though it does not explicitly name cancel_invoice as the alternative.

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?

It states the creation context (draft for an issued invoice) and prescribes follow-up actions: use update_document to adjust prices and finalize_document to issue. It lacks explicit guidance on when to choose this over cancel_invoice or other sibling tools.

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