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

With no annotations, the description carries the behavioral burden and does reasonably well: it discloses defaults (platform set's device frame, positioned next to the main phone inheriting its size, rotation, shadow), z-order ('extra phones paint above the main phone, in the order they were added'), and the return value. It omits permissions/auth or mutation risk context, so it is not exhaustive.

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?

Five tight sentences, front-loaded with the core action, then defaults, an input hint, paint order, and the return value. Every sentence adds distinct information and there is no filler despite the parameter complexity.

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?

Given no annotations and no output schema, the description compensates by stating the return value (phoneId) and default behavior, which is helpful. However, with 36 parameters it leaves the majority of the parameter surface unexplained, so it is adequate but not complete for a tool of this complexity.

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 description coverage is only 36% across 36 parameters, so the description must compensate but largely does not. It adds meaning only to imageUrl (upload_image hint) and implicitly to deviceId/color defaults, leaving the large focusOverlay*, shadow*, and fade families undocumented in both places.

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 ('Add') and resource ('another phone to a screenshot card in the open editor'), and clarifies it is a secondary phone distinct from the main phone. It does not explicitly name the sibling tools it contrasts with (update_phone, remove_phone, add_screenshot), so it falls just short of full sibling differentiation.

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?

Provides clear context for use: it must be applied in the open editor to a screenshot card, and imageUrl should come from upload_image with type screenshot, a useful cross-tool referral. No explicit when-not guidance or exclusion conditions are given, keeping it below a 5.

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