Zvaliduje a uloží design (logo/text na stranách trička) a vrátí orientační cenu potisku + vrstvy s nahranými URL k použití v create_order.
| Name | Required | Description | Default |
|---|---|---|---|
| layers | Yes | vrstvy: {type:'image'|'text', side:'front'|'back'|'sideLeft'|'sideRight', x,y,width,height v % 0–100, rotation?, src? (URL nebo data:URL obrázku), text?, fontFamily?, fontSize?, fill?} | |
| colorId | No | ||
| product | Yes | ||
| previewBackDataUrl | No | ||
| previewFrontDataUrl | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=false and idempotentHint=false, and the description adds that the tool validates and saves a design, indicating a persistent side effect. It also discloses that it returns an indicative price and layers with uploaded URLs, which is useful behavioral context beyond the annotations. No contradiction found.
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 efficiently states the action, object, and result without redundancy. Every clause adds information: validation, saving, the design scope, and the returned data for create_order.
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?
The description covers the overall purpose and return value (price and layers), but with 5 parameters and no output schema, the absence of parameter explanations and edge cases leaves gaps. It does not mention required fields (product, layers) or the meaning of preview data URLs, so while the main context is clear, it is not fully 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 20% (only 'layers' has a description). The top-level description mentions 'logo/text on t-shirt sides' which loosely relates to the 'layers' parameter but does not explain `colorId`, `product`, `previewBackDataUrl`, or `previewFrontDataUrl`. With such low coverage, the description fails to compensate for the undocumented parameters.
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 validates and saves a design (logo/text on t-shirt sides) and returns an indicative price plus layers for use in create_order. This distinguishes it from siblings like create_order (which places the order) and get_quote (which presumably only quotes) by specifying the resource (design) and the output (prepared layers with URLs).
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 the tool is a precursor to create_order by stating the result is for use in create_order, giving clear context for when to use it. However, it does not explicitly say when not to use it or name alternatives (e.g., use get_quote for price-only queries), so it lacks explicit exclusions.
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.
Each tool targets a distinct resource or workflow step: product catalog (list_products), price estimation (get_quote), design creation (create_design), order placement (create_order), and status tracking (get_order_status). The pricing overlap between create_design and get_quote is resolved by clear descriptions: one validates and saves a design with an estimated print cost, the other calculates a full shirt quote independently.
All tool names follow a consistent verb_noun pattern: create_ for creation, get_ for retrieval, and list_ for listing. There are no mixed conventions or vague verbs, making the naming predictable and easy to navigate.
Five tools is well-sized for the server's purpose as a custom apparel configurator. It covers the essential steps—product browsing, quoting, design, ordering, and status—without redundancy or unnecessary bulk.
The tools provide a complete ordering flow: discover products, get a quote, create a design, place an order, and check status. Minor gaps exist, such as no design management (list/update/delete) or order cancellation, but these are not critical to the core configuration and ordering workflow.
