eda_dmt_editor_control_create_split_screen

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

No annotations are provided, so the description carries the full burden. It discloses the return value shape (sourceSplitScreenId and newSplitScreenId) and that it may return undefined, which is useful. However, it does not mention side effects, such as whether the split screen is immediately visible, whether it requires a specific editor state, or what happens if the tabId is invalid. The description is minimal and does not add behavioral context beyond the signature.

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 description is compact, containing the signature, a short Chinese phrase '创建分屏' (create split screen), and a return value explanation. It is front-loaded with the action and signature. The bilingual content is slightly redundant but not wasteful. It earns a 4 for being concise and structured, though the Chinese description is not necessary.

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 the tool has no annotations, no output schema, and only a generic args array, the description should provide more context. It explains the return value but lacks information about the splitScreenType enum values, how to obtain a tabId, and what 'undefined' means in practice. The sibling tools suggest a rich split-screen management system, and this description does not fully equip an agent to call it correctly without additional lookups.

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?

The schema has 100% description coverage for its two parameters (args and windowId), but the descriptions are generic: 'args' is a JSON array in official signature order, and 'windowId' targets a window. The description adds the method signature with parameter names and types (splitScreenType: EDMT_EditorSplitScreenDirection, tabId: string), which helps map args to meaningful values. However, it does not explain the enum values for splitScreenType or the format of tabId. Baseline 3 is appropriate since the schema covers the parameters but the description adds some semantic value.

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 description states a specific verb ('create') and resource ('split screen'), and includes the method signature with parameter types and return type. It is clear this tool creates a split screen in the editor. However, it does not explicitly differentiate from sibling tools like activate_split_screen or get_split_screen_tree, though the name and action are distinct enough.

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 description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, such as needing an active document or tab, nor does it explain when a split screen would be appropriate. The only context is the signature and a brief Chinese description, which implies usage but does not state it.

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