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

Annotations already declare a non-readonly, non-destructive, non-idempotent write; the description adds substantive behavior beyond that: what actually gets written (1-field minimal definition), what the template copy mutates (fields carried over, visibility reset to the target scope, adminsql stripped for non-admins, buttons/template_file inherited), and the exact auth requirement with the resulting 403. Nothing here contradicts 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?

The German block is dense but front-loaded: creation action first, template behavior second, permissions last. The trailing "| EN: form, form definition, fields, template, PDF, submission" is keyword padding rather than agent-relevant content, which costs it a point.

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 mutating create tool with no output schema, it covers what is created, the auth precondition, the template-copy side effects, and the mandatory next step (onto_formdef_save). An agent has enough to invoke it correctly and chain it; the only residual gap is whether the new form's identifier is returned, which the naming convention makes inferable.

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 baseline is 3, but the description adds real semantics for the template path — field takeover, visibility rewriting, adminsql removal. It does not cover the `formdef` or `answer_type` alternatives, and it calls the parameter "from_udid" while the schema names it `from`, a small mismatch an agent must resolve.

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 first two sentences state a specific verb and resource ("NEUES Formular anlegen") and precisely scope the effect: it creates the form object plus a minimal valid 1-field definition. It explicitly separates itself from the sibling onto_formdef_save (used afterwards to extend) and from onto_formdef_list_templates (source of the template udid), so an agent can route correctly.

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 gives clear usage context: call this first, then extend with onto_formdef_save, and use the from/template path when copying an existing definition (with a follow-up check of buttons/template_file). What's missing is explicit guidance on the alternative `formdef` path (pass a complete definition instead of the minimal scaffold) and on when NOT to create a copy at all.

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