Siren

upload_product_screen

Upload a brand asset (product photo, app screenshot, packaging) into Brand DNA and store it on R2. Pass image_url (https PNG/JPG/WebP) or image_base64.

Two ways to file it:

Send description (and optionally kind, use_when, tags, name): Siren trusts your words and files the asset as-is. No read.
Send only the file: Gemini reads the picture and writes name, kind, description, use_when, tags itself. scan_status goes scanning → ready in about 8 seconds; poll list_product_screens.

kind is free text ("product photo", "dashboard screenshot", "packaging"), there is no fixed list. A brief that names an asset ("advertise the pink handbag") pulls that file into the still. screen_type / device / theme only matter for device-framed screenshot masters.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`kind`	No	Free-text kind: product photo, dashboard screenshot, packaging, logo, team photo.
`name`	No	Human-readable name for the asset or run.
`tags`	No	Short lowercase tags for search, e.g. ["dashboard", "dark-mode"].
`theme`	No	UI theme in the screenshot: light, dark, or unknown.	unknown
`device`	No	Device the screenshot was taken on: phone, tablet, desktop, or none.	phone
`use_when`	No	When Siren should reach for this asset, e.g. "any post about the analytics page".
`image_url`	No	Public https URL of a PNG, JPG, or WebP to store as a brand asset.
`description`	No	What the picture shows and what it is for, in your words. When set, Siren files the asset without reading it.
`screen_type`	No	Screen role: feature, hero, onboarding, settings, or marketing.	feature
`image_base64`	No	The image bytes as base64, if you have no URL.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed10 schema fields changedSep 9, 2026

addedInput schema / properties / description / description

Added value: +"What the picture shows and what it is for, in your words. When set, Siren files the asset without reading it."

addedInput schema / properties / device / description

Added value: +"Device the screenshot was taken on: phone, tablet, desktop, or none."

addedInput schema / properties / image_base64 / description

Added value: +"The image bytes as base64, if you have no URL."

addedInput schema / properties / image_url / description

Added value: +"Public https URL of a PNG, JPG, or WebP to store as a brand asset."

addedInput schema / properties / kind / description

Added value: +"Free-text kind: product photo, dashboard screenshot, packaging, logo, team photo."

addedInput schema / properties / name / description

Added value: +"Human-readable name for the asset or run."

addedInput schema / properties / screen_type / description

Added value: +"Screen role: feature, hero, onboarding, settings, or marketing."

addedInput schema / properties / tags / description

Added value: +"Short lowercase tags for search, e.g. [\"dashboard\", \"dark-mode\"]."

addedInput schema / properties / theme / description

Added value: +"UI theme in the screenshot: light, dark, or unknown."

addedInput schema / properties / use_when / description

Added value: +"When Siren should reach for this asset, e.g. \"any post about the analytics page\"."

First observedSep 9, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Beyond the annotations, the description discloses meaningful behavior: Gemini reads the image and writes metadata itself, scan_status transitions from scanning to ready in about 8 seconds, Siren trusts provided descriptions and does not read the file, and screen_type/device/theme only matter for device-framed screenshot masters. This goes well beyond the generic annotation hints.

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?

The description is well-structured with a clear opening, bulleted modes, and a concise clarification about kind and device-framing parameters. Despite covering 10 parameters, every sentence earns its place and the bullets make the two ingestion paths easy to parse.

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?

Given the tool's complexity and the absence of schema descriptions, the description is remarkably complete: it covers input formats, both filing modes, auto-generated metadata, async scanning status, polling guidance, free-text kind semantics, and parameter scoping. Since an output schema exists, the description does not need to explain return values, and nothing critical is missing for invoking the tool correctly.

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?

With 0% schema description coverage, the description carries the burden and mostly succeeds: it explains image_url vs image_base64 alternatives, optional metadata parameters, free-text kind with no fixed list, and the limited relevance of screen_type/device/theme. It leaves some parameters like name, tags, and use_when only implied rather than fully defined, but the semantics are reasonably inferable.

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 opening sentence states a specific action (upload a brand asset into Brand DNA and store it on R2) with concrete example content types. It clearly distinguishes this upload tool from sibling tools like update_product_screen, delete_product_screen, and list_product_screens by describing the core upload-and-file behavior.

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

Usage Guidelines4/5

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

The description gives clear context for when to use each mode: send description to file as-is, or send only the file to let Gemini generate metadata. It also tells the agent to poll list_product_screens after auto-scanning, but it does not explicitly contrast this tool with update_product_screen or other alternatives.

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

All Siren tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.