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

Goes well beyond the annotations (destructiveHint/openWorld/idempotent): it discloses the 403 authorization failure mode, admin-only restrictions on public:true/PUBLIC scope/SQL conditions, the visibility-vs-execution distinction tied to body.scopes[], and the hidden_actions opt-out a scope manager can use. This is exactly the extra mutation context the annotations cannot carry.

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?

Front-loads the verb and the PFLICHT requirement well, but the paragraph is long and drifts into tangential rules (members cloning platform actions, hidden_actions suppression) that are not needed to invoke the tool, and it ends with keyword-stuffed tags ('action, button, definition, gate...'). Useful content, but not tightly scoped.

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 destructive, non-open-world mutation with no output schema, the definition supplies permissions, scope semantics, an example payload and admin carve-outs — enough to call it correctly. It does not describe the success response or what happens on update versus create, a minor remaining gap.

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 already 100%, so the non-zero value comes from the description unpacking body — a JSON string whose scopes[] is mandatory, plus a worked example with object_types, roles and action.type 'form_answer' linking the answer to the object. That adds real meaning beyond the schema's terse body 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 pair and resource: 'Actiondef anlegen/aendern (Button am Objekt)' — create/update an action definition (object button). An agent can immediately distinguish it from siblings onto_actiondef_delete and onto_actiondef_list without opening any 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 strong usage conditions: body.scopes is mandatory, the caller must be Manager (can_manage_scope) or Writer (can_write) on those scopes or get 403, PUBLIC scope 15 is admin-only, and exactly one target scope is allowed at creation. It stops short of explicitly routing to sibling tools (list/delete) for other operations, so it is clear context but not full alternative coverage.

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