finish_local_garment_uploadSecond step only for local garment images already prepared with prepare_local_garment_upload and uploaded to every returned target. Classify each upload_handle as a full/detail front/back/side asset. Do not use this for ChatGPT attachments or arbitrary public URLs.
| Name | Required | Description | Default |
|---|---|---|---|
| garments | Yes | Garments assembled from owned upload handles returned by prepare_local_garment_upload |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are all false (readOnlyHint: false, destructiveHint: false), so the description carries the disclosure burden. It explains the prerequisite and classification action but does not reveal side effects like whether it finalizes the garment, consumes handles, or is idempotent. Some scope constraints are added, but deeper behavior remains opaque.
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 three sentences, front-loaded with the prerequisite ('Second step only'), and every sentence adds value: prerequisite, action, and exclusion. No fluff or redundancy.
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 output schema, the description doesn't need to explain return values. It covers the two-step flow, the requirement for prepared/uploaded handles, the classification scope, and explicit non-uses. It could mention that it ultimately creates/updates garment records, but the schema's garments array implies this. Fairly complete for an agent.
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 detailed field explanations (e.g., upload_handle description, asset_kind enum, processing_mode). The description only restates the classification concept (full/detail front/back/side) without adding new parameter-level semantics beyond what the schema already provides. Baseline 3 applies.
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 tool's purpose: 'Second step only for local garment images already prepared with prepare_local_garment_upload' and 'Classify each upload_handle as a full/detail front/back/side asset.' It explicitly distinguishes itself from tools for ChatGPT attachments or public URLs, making it highly specific.
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 gives explicit usage conditions: 'Second step only' and 'uploaded to every returned target.' It also includes a clear exclusion: 'Do not use this for ChatGPT attachments or arbitrary public URLs.' This effectively tells the agent when to use it versus alternatives.
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.