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

Annotations already declare non-read-only, non-destructive, non-idempotent, closed-world. The description adds substantive behavior beyond that: the result is a draft, amendments keep the existing contract in force with a numbered scheme (<Vertrag>-N1), and versions supersede the contract from their lease start. No mention of permissions or what the draft inherits from the original.

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?

One dense sentence, front-loaded with the action and then the mode breakdown in a predictable 'amendment = … version = …' pattern. 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 2-parameter mutation with no output schema, the mode semantics are well covered, but it doesn't say what the newly created draft contains (copied fields), whether the caller needs specific permissions, or what identifier comes back.

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 50%: id is self-evident, and kind's enum values get no schema description. The description compensates by explaining precisely what each enum value means and its consequence for the original contract, which is exactly the meaning the enum lacks.

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?

Specific verb+resource: 'einen neuen Entwurf anlegen' for an existing contract, and it names the two modes by keyword. It stops short of explicitly contrasting with update_contract or create_contract, so sibling differentiation relies on inference.

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?

Constrains usage to a 'laufenden Vertrag' and disambiguates the two modes: amendment for an addendum where the contract stays in force, version for a replacement that supersedes the contract from its lease start. Clear context, but no explicit when-not or alternative-tool routing.

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