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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so the agent knows this is an external, non-idempotent write. The description adds genuine value beyond that by explaining the mail routing: without own SMTP it goes via brandbill with the invoice e-mail as Reply-To, otherwise the sender account or default account. It still does not say whether the document is marked as sent afterwards, whether resending duplicates, or what happens on delivery failure.

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 compact sentences with the action front-loaded and the routing detail second. No filler. Slight density cost from the parenthetical, but every clause carries information.

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 side-effecting tool with no output schema and no annotation detail beyond hints, the description covers the routing model but omits the observable outcome (does the document transition to 'sent'?) and any failure semantics. Adequate to invoke, not complete enough to predict consequences.

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 17% (only 'id' is documented), so the description has to compensate. It does clarify the one non-obvious parameter indirectly: 'Absenderkonto bzw. Standardkonto' explains how mail_account_id behaves when omitted. The remaining parameters (to, cc, subject, body) are self-evident from their names and formats, but nothing is said about them in the description.

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 plus the delivery channel and format: an issued document is sent as a PDF by e-mail. The qualifier 'Ausgestellten' also narrows scope to finalized documents, which is meaningful. It does not, however, distinguish this from the sibling mark_sent, which is the obvious confusion point for an agent.

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 word 'Ausgestellten' implies the precondition that the document must already be issued, which is implied rather than stated as a rule. There is no explicit when-not guidance and no mention of the alternative mark_sent for merely flagging a document as sent without sending mail. Usage is therefore inferable but not disambiguated.

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