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

Annotations already declare readOnly=false, idempotent=true and destructive=false, so the safety profile is covered. The description adds two behaviors the annotations cannot express: the document number is immutable, and the update is partial with 'lines' fully replacing the existing line list — the latter being the main way an agent could unintentionally lose data. It omits whether empty strings clear fields and whether omitting 'lines' preserves them.

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 short clauses, no filler, with the immutability constraint front-loaded before the update semantics. Every clause carries information an agent needs to call the tool correctly.

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 16-parameter mutation tool with a nested line array and no output schema, the description covers the crucial patch semantics but says nothing about what a successful call returns, how validation errors surface, or what happens with an empty 'lines' array. Adequate as a minimum, but thin given the tool's complexity.

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 63%, so several fields (intro_text, closing_text, customer_city, customer_number, customer_street, customer_postal_code) carry no explanation anywhere. The description compensates for the most consequential gap by defining cross-parameter merge semantics ('only passed fields change', 'lines replaces the list'), which the per-property schema text does not state globally.

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 plus resource ('Einen Lieferschein ändern') and immediately adds a scope constraint ('die Nummer bleibt'), so the agent knows this is a modification of an existing document, not a create/delete. It does not name the sibling tools (create_delivery_note, delete_delivery_note) explicitly, so differentiation rests on the name and that one clause.

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?

'Nur übergebene Felder werden geändert' implies a patch-style call and warns against sending the full object, which is real usage guidance. There is no explicit when-to-use versus when-not guidance (e.g. create_delivery_note for new notes, delete_delivery_note for removal) and no prerequisites or permission notes.

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