Start a purchase of a paid Assetzaar product for the connected account. Requires an agent key (Authorization: Bearer azr_…, created at assetzaar.com/account/agent-keys). Returns a Stripe approval URL — the HUMAN must open it and approve payment; the agent can never charge anyone by itself. After approval, call check_purchase, then install.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | The product slug to buy. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it discloses the need for an agent key, the return of a Stripe approval URL, and that the agent cannot charge anyone by itself. It also outlines the post-approval steps, providing strong behavioral context beyond basic operation.
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: purpose, auth/return value, and next steps. Each sentence adds distinct value with no redundancy, making it highly concise and well-structured.
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?
Despite lacking an output schema and annotations, the description supplies the essential return value (Stripe approval URL), required authentication, and the follow-up workflow. This is sufficient for a tool with one parameter and a simple flow.
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 already covers the 'slug' parameter with 'The product slug to buy,' achieving 100% coverage. The description adds little beyond this, only framing it as a paid product, so a baseline score of 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 'Start a purchase of a paid Assetzaar product for the connected account,' using a specific verb and resource. It distinguishes itself from siblings like check_purchase, install, and search by focusing on initiating the purchase flow.
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?
It explicitly requires an agent key and instructs the user to 'call check_purchase, then install' after approval. This provides a clear workflow and tells the agent when to use this tool relative to alternatives, along with the critical human-approval step.
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 have clearly distinct purposes, but there is some overlap: search and search_components both find products (one whole marketplace, one UI components only), and get_component and inspect both retrieve product information (one for source, one for manifest). These are distinguishable by their descriptions and use cases.
The tools follow a mostly consistent verb-based pattern with snake_case (check_purchase, get_component, search_components), but three tools are single verbs without an object (inspect, install, purchase). This is a minor deviation from the verb_noun convention used by the others.
Seven tools is well-scoped for a marketplace server. Each tool covers a necessary step in the workflow (search, evaluate, purchase, install) without bloat, and there are no redundant utilities.
The tool set covers the full marketplace lifecycle: discovery (search, search_components), evaluation (inspect, get_component), acquisition (purchase, check_purchase), and installation (install). The flow from search to install is seamless, with no obvious dead ends or missing critical operations.