Skip to main content
Glama

product_set_images

Destructive

Replace a product's images by uploading local files, setting the first as the main image and the remaining as gallery images, with an optional force flag to overwrite existing ones.

Instructions

Replace a product's images. files is a list of absolute paths to local image files (jpg, jpeg, png, webp, gif). First file becomes the main image (image_id); rest are gallery images. Runs Voog's 3-step asset upload protocol per file (POST /assets → PUT upload_url → PUT confirm), then PUTs {image_id, assets:[{id:n}]} to /products/{id}. Refuses to replace existing images unless force=true. If any single upload fails, the product is NOT updated — successful uploads are surfaced in uploaded for manual re-linking.

Gallery ORDER is applied by re-reading it back and repeating the PUT: Voog lands the requested order only about half the time on the first write (200 either way). If the order still has not taken, the call comes back as an ERROR carrying order_verified: false and the stored_asset_ids Voog actually holds. In that case every image IS linked and only the sequence is wrong — do NOT re-run this tool to fix it, that re-uploads every file as a new asset. Re-send just the order via voog_ecommerce_api_call PUT /products/{id}.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
siteYesSite name from voog_list_sites
filesYesAbsolute paths to local image files. First is the main image, rest are gallery.
forceNoRequired to replace existing images. Defensive opt-in like page_delete — even with the destructiveHint annotation, the server refuses without force=true.
product_idYesVoog ecommerce product id
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only provide destructiveHint=true, but the description adds substantial context: the multi-step upload protocol, atomic failure behavior (product not updated if any upload fails), the gallery order race condition, and the specific error payload (order_verified: false). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Though long, every sentence carries essential operational detail. It front-loads the purpose, then logically sequences the upload protocol, failure modes, and remediation steps. No redundant content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex mutation with no output schema, the description covers all critical aspects: prerequisites, exact HTTP flow, failure atomicity, gallery order verification, and alternative remediation. It leaves no operational gaps for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers all 4 parameters at 100%, so baseline is 3. The description adds meaning by explaining files list semantics (first is main image), the force requirement (defensive opt-in like page_delete), and the relationship between site and product_id. This exceeds schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Replace a product's images', a specific verb+resource statement that clearly identifies the action. It distinguishes itself from siblings like asset_upload and product_update by focusing on image replacement for a product.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use (replacing existing images), requires force=true as a prerequisite, and provides an exclusion: do NOT re-run to fix gallery order, instead use voog_ecommerce_api_call. This gives clear when/when-not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/runnel/voog-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server