Create a private shelf
foliade_create_shelfCreates a shelf as a draft. The Distributeur plan is required; nothing is published automatically.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| patch | Yes |
foliade_create_shelfCreates a shelf as a draft. The Distributeur plan is required; nothing is published automatically.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| patch | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No contradiction with annotations; readOnly=false and destructive=false are consistent with creating an unpublished draft. The description adds the plan requirement and the no-auto-publish side effect, but it doesn't mention error behavior, access/visibility of the draft, or how to locate the created shelf afterward.
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?
Two short sentences with no filler; the core behavior is front-loaded and the plan requirement is stated in a single clause. This is an efficient description.
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?
For a creation tool with a large ShelfPatch object, no output schema, and 0% parameter coverage in the description, this is too thin. It tells the agent the draft state and plan requirement but not what to pass in the patch, what success returns, or what follow-up calls (e.g., publish) are needed.
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 0% and the description adds nothing about the 'name' or 'patch' parameters. The 'patch' parameter is especially unclear: an agent isn't told that it is a ShelfPatch of settings to apply to the new shelf, and the French property names in the schema are left unexplained.
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?
States a specific action and resource ('Creates a shelf') and clarifies the created object's state ('as a draft', 'nothing is published automatically'). This distinguishes it from update/publish/list siblings by operation, though it doesn't explicitly name an alternative and doesn't carry the title's 'private' qualifier into the description.
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?
Provides a clear precondition ('Distributeur plan is required') and sets the expectation that publication is a separate step. It never explicitly contrasts this with foliade_update_shelf or foliade_publish_catalogue, so the when/why to choose it is mostly implied by the verb 'Creates'.
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.