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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral trait: unknown props fields are silently ignored, which warns the agent about quiet failure. It says nothing about where the widget lands, whether board state is required, or what is returned on success.

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 sentences with zero filler; the core action is front-loaded and the props caveat follows immediately. Every clause carries information the agent needs.

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 mutation tool with a free-form nested props object and no output schema, the definition covers the biggest unknown (props) but leaves out the return value, the effect of omitting position, and any board prerequisite. Adequate to call correctly in the happy path, thin for anything unusual.

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 only 50%, but the two documented params (board_id default-to-last-board, position with named slots or {x,y,w,h} percent) are well served by the schema itself. The description compensates for the undocumented free-form "props" object by pointing to list_widget_types and flagging that unknown fields are ignored, though it adds nothing about the 31-value "type" enum.

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?

"Fügt ein Widget hinzu" gives a specific verb (add) and resource (widget), which cleanly separates it from update_widget, remove_widget and list_widget_types in the sibling list. It never states that the widget is added to a board/screen, so the target container is left implicit.

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?

The pointer "props siehe list_widget_types" is a real workflow hint that routes the agent to the sibling that defines valid props. Beyond that there is no when-to-use, no prerequisite (e.g. an existing board), and no guidance on choosing add_widget vs apply_template or update_widget for an already-present widget.

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