create_ai_pack_draftCreate an owner-bound AI Pack listing with the complete buyer guide and two concrete example uses. Accept current terms first. Free drafts do not require Stripe Connect.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| models | Yes | ||
| listing | Yes | ||
| category | Yes | ||
| priceUsd | No | ||
| description | Yes | ||
| capabilities | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the burden of explaining side effects. It mentions the need to accept terms and that free drafts avoid Stripe Connect, which are useful preconditions. However, it does not state what happens to existing drafts, whether the draft becomes visible, or if any other state is modified, so transparency is partial.
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 only two sentences, yet it conveys the key purpose, ownership, required content, and payment-related exceptions. It is well-structured, directly to the point, and contains no redundant or verbose phrasing.
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 does not mention the return value or output of the tool, and the absence of an output schema leaves the agent without expectations. It also fails to explain the nested structure of the 'listing' object, which is complex and could benefit from clarification, making the description incomplete 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?
The schema provides no parameter descriptions, and the tool description only adds minimal guidance by referencing 'buyer guide' and 'two concrete example uses'—implicitly mapping to the listing fields and exampleUses array. It fails to explain the purpose of individual parameters like 'capabilities', 'models', or 'priceUsd', leaving the agent to guess from names and constraints.
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 verb 'Create' and a specific object 'owner-bound AI Pack listing' with required contents (buyer guide, two concrete example uses). It distinguishes this from a general draft by specifying ownership and completeness, making the tool's purpose unambiguous.
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 preconditions (accept terms, no Stripe Connect for free drafts) but does not mention any alternative tools or when to prefer this over others like 'update_ai_pack_draft' or 'publish_ai_pack'. It lacks explicit guidance on when to use this tool versus sibling tools, leaving the agent to infer context from the name alone.
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 roles across the pack lifecycle, but the growth/audition/quote cluster and multiple get_*_report/profile/readiness tools could cause an agent to pause and read descriptions carefully. The descriptions do help separate them, so the ambiguity is minor rather than severe.
All tool names follow a consistent lowercase snake_case verb_noun pattern, with prefixes like list_, get_, run_, create_, update_, and upload_ used uniformly. The different noun segments reflect different resources, not inconsistent naming conventions.
With 26 tools, the surface is slightly heavy, but it maps to a broad set of legitimate operations: drafting, publishing, auditing, running, growth, quoting, model listing, and upload/download workflows. Each tool appears purposeful, and none are obvious duplicates.
The tool set covers most major lifecycle actions, but there are notable gaps such as no delete/unpublish for packs or drafts, no simple get_ai_pack by ID, and no cancel operation for runs or auditions. These missing operations prevent full CRUD/lifecycle coverage.