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

Annotations already declare readOnly/idempotent/non-destructive, and the description reinforces this with 'er wordt niets opgeslagen' plus a statement of what is returned ('een design_id dat het hele ontwerp bevat'). It goes further by spelling out fallback behaviour for omitted optional parameters (original colour, spacious composition, default room). It does not describe whether the design_id expires or how it later feeds update_wallpaper_design/render_wallpaper_preview.

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?

Roughly five sentences, front-loaded with what the tool does and the target wall size, then parameter semantics, then the return value, then the exclusion and alternative. Every clause carries information: defaults, data sources, and the sibling pointer.

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 7-parameter tool with a nested object and no output schema, the description covers the return value (design_id), the no-persistence guarantee, defaults for all optional parameters, and the boundary against the own-image sibling. Only the product_id source is left implicit and there is no hint about lifecycle of the returned design.

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?

With 0% schema description coverage the description carries the load, and it does: wall_cm as own wall size in cm, material as vlies/vinyl, colour as 'uitvoering' and composition as 'compositie' from the product link, room as the room of the mood image taken from 'rooms' in the response, and furniture=false showing the room unfurnished. product_id is only implied via 'uit search_catalog', and the default behaviour is stated rather than the accepted value formats.

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 opening sentence names a specific verb and resource ('Start een ontwerp voor catalogusbehang') and scopes the input source ('uit search_catalog'), the sizing unit ('eigen muurmaat in cm') and the material options ('vlies of vinyl'). It also points to the sibling that handles the adjacent case ('start_own_image_wallpaper_design'), so an agent can separate the two without opening either 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?

Guidance is explicit where it matters: use this tool for catalog wallpaper but use start_own_image_wallpaper_design for a design from your own image, and 'Fotoreliëf kan niet' rules out one case outright. It also explains where the optional colour/composition/room values should come from (the product link, the 'rooms' list in the response). No explicit routing against get_wallpaper_design or render_wallpaper_preview, hence not a 5.

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