eda_dmt_folder_create_folder

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

With no annotations provided, the description carries the burden of behavioral disclosure. It does disclose the return value: a folder UUID string, or undefined if creation fails, which is useful. It does not disclose side effects (e.g., whether the folder is immediately visible, whether it requires an active team context, or whether duplicate names are rejected). The description adds the failure signal (undefined) but lacks deeper behavioral context like persistence or validation rules.

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: a signature line, a Chinese one-liner, and a return-value note. It front-loads the essential call signature and return behavior. The Chinese '创建文件夹' is redundant with the signature but harmless. It earns a 4 because it is efficient and structured, though the redundancy and lack of parameter explanations prevent a 5.

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 create operation with no output schema and no annotations, the description provides the signature, return type, and failure signal, which covers the basics. It does not explain the context of teamUuid (e.g., how to obtain it, whether it is required to be the current team), nor does it mention any constraints like folder name uniqueness or parent folder existence. Given the tool's simplicity, this is adequate but not complete; an agent might need to consult sibling tools like eda_dmt_team_get_all_teams_info to resolve teamUuid.

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 input schema has 100% description coverage for its two top-level parameters (args array and windowId), but the actual function parameters (folderName, teamUuid, parentFolderUuid, description) are only listed in the description's signature line. The description adds meaning by showing the order and optionality of these parameters, which is valuable given the args array format. However, it does not explain the semantics of each parameter beyond their names, such as what teamUuid refers to or how parentFolderUuid affects the folder hierarchy.

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 and resource: 'dmt_Folder.createFolder' creates a folder, with parameters for folder name, team UUID, parent folder UUID, and description. It clearly distinguishes from siblings like eda_dmt_folder_delete_folder, eda_dmt_folder_get_all_folders_uuid, and eda_dmt_folder_modify_folder_name. However, it doesn't explicitly state the domain context (e.g., that it creates a folder in a team's folder tree) beyond the parameter names, and the Chinese '创建文件夹' is a direct restatement of the name.

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 implies usage by listing the required parameters (folderName, teamUuid) and optional ones (parentFolderUuid, description), which tells an agent what is needed to create a folder. It does not explicitly state when to use this tool versus alternatives like eda_dmt_folder_move_folder_to_folder or eda_dmt_folder_modify_folder_name, nor does it mention prerequisites like team membership or permissions. The context is clear enough for a simple create operation, but there is no explicit when/when-not guidance.

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