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

Annotations already declare readOnlyHint=false and destructiveHint=false, and the description materially extends this: the upload stays a draft, nothing is booked, nobody is notified, recognition auto-fills date/amount/supplier/category, and an API key with app access is required. This is exactly the mutation-side context annotations alone cannot convey.

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?

The purpose and its safe-to-run nature are front-loaded, but the opening two sentences restate the same 'upload as a draft' idea ('Upload a receipt file as a draft' / 'Uploads a PDF, PNG or JPG from a URL to Belege as a draft'), which is mild redundancy.

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 correctly covers the return ('the response shows what it found'), the draft lifecycle, the recognition behavior, and the auth requirement. Both parameters are required and documented, leaving nothing an agent needs missing.

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 the schema already documents file_url (PDF/PNG/JPG URL) and the kind enum. The description restates the accepted file types but adds no syntax or format detail for the kind parameter, 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+resource (upload a receipt file) and its scope (as a draft in Belege), plus the OCR-like recognition it triggers and what the response returns. This clearly separates it from siblings like sevdesk_list_vouchers or sevdesk_mark_voucher_paid without opening a schema.

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 context: upload a receipt from a URL, equivalent to dragging into the overview, and notes it 'runs without asking first' plus a pre-completion check on category/tax rule. It does not explicitly name a sibling alternative, so it stops short of the 5 tier, but the when-to-use guidance is solid.

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