update_ai_pack_draftUpdate seller-owned public metadata; immutable pack versions are never overwritten.
| Name | Required | Description | Default |
|---|---|---|---|
| tags | No | ||
| models | No | ||
| listing | No | ||
| priceUsd | No | ||
| productId | Yes | Tetrees AI Pack product id | |
| capabilities | No | ||
| businessUseCase | No | ||
| shortDescription | No |
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?
The description adds important behavioral context beyond the annotations by stating that immutable pack versions are never overwritten, which clarifies a non-destructive guarantee. Combined with readOnlyHint=false and destructiveHint=false, this gives a reasonable picture of side effects, though it does not mention validation failures or partial update behavior.
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, tightly worded sentence that front-loads the action and object. It avoids redundancy and does not waste words on filler.
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 the large nested schema and no output schema, the description is too terse to be fully complete. It does not explain how this update interacts with draft versus published states, whether the update is partial or full replacement, or what response the caller should expect.
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 13%, with only productId having a description in the schema. The tool description does not compensate by explaining key parameters like priceUsd, capabilities, models, tags, shortDescription, or the complex nested listing object, leaving much of the parameter semantics to inference from names.
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 ('Update') and the object ('seller-owned public metadata' / 'AI Pack listing details'). It also distinguishes this from related tools by noting that immutable pack versions are never overwritten, which separates it from create/publish operations.
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 for updating listing metadata but does not explicitly state when to prefer it over create_ai_pack_draft, submit_ai_pack_for_audition, or publish_ai_pack. Sibling tool names provide context, but the description itself lacks direct usage guidance or 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 are clearly distinct by action and resource, though several clusters (accept/propose/select/list growth, prepare/execute/run) require careful reading of descriptions to avoid confusion.
All tool names follow a consistent verb_noun snake_case pattern, with clear action prefixes and descriptive resource nouns.
With 26 tools, the set exceeds the recommended range and feels heavy, even though the domain covers publishing, runtime, growth, and reporting workflows.
The toolkit covers the main AI pack lifecycle—authoring, publishing, acquisition, running, searching, and reporting—but lacks explicit delete/revoke operations for drafts or entitlements.