create_tagCreate a new tag for organizing assets (garments, models, outfits, files, results, locations). Requires an active company workspace.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Tag name (unique within the company) | |
| color | No | Optional hex color, e.g. '#22C55E' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=false and destructiveHint=false. The description adds the workspace requirement but doesn't disclose uniqueness enforcement or idempotency-related behavior (e.g., what happens if a duplicate name is submitted). No contradiction with annotations.
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 a single front-loaded sentence that communicates the core functionality. The asset type list is slightly detailed but remains compact and useful.
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 simple create tool with full schema coverage and no output schema, the description and schema together provide sufficient guidance. It could mention return values or duplicate-name behavior, but these are not critical for tool selection and invocation.
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 100%, with both parameters fully described (name with uniqueness and maxLength; color with format example). The description adds no parameter-specific meaning beyond listing asset types, so baseline 3 is appropriate.
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 clearly states the action ('Create a new tag'), the resource ('for organizing assets'), and enumerates the asset types. This distinguishes it from sibling tools like list_tags and get_items_by_tag, which have different purposes.
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 a clear precondition ('Requires an active company workspace') and indicates a broad use case (organizing assets). It doesn't explicitly name alternatives or when-not-to-use scenarios, but the context is sufficient for a simple create tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target distinct resources and have detailed descriptions, but several closely related families exist: create_credit_checkout_session vs mcp_create_credit_checkout_session, the propose_brief/confirm_brief/update_brief lifecycle, and the many avatar/upload entry points. An agent must read long caveats carefully to avoid selecting the wrong tool.
The vast majority of tool names follow a predictable snake_case verb_noun pattern (list_*, get_*, create_*, update_*, propose_*). The mcp_* prefix group and varied creation verbs (create/upload/save/add/generate) are minor deviations, though mcp_create_credit_checkout_session duplicating create_credit_checkout_session adds some confusion.
With 67 tools, this is an extreme mismatch by the rubric's own 50+ threshold, far beyond the typical 3-15 well-scoped range. Many tools are narrow lifecycle steps such as two-phase local uploads, app-only montage internals, and multiple ArtDirection authoring variants, making the agent-facing surface very heavy.
The core generation, brief, montage, and QA workflows are covered thoroughly with polling and result retrieval. However, notable lifecycle gaps exist: outfits, locations, avatars, and tags mostly have create/list/get but no update or delete, and delete_template is the only delete tool in the entire set.