Skip to main content
Glama

Upload images to a Stick site

upload_images
Read-only

Opens an image picker directly in the conversation; this call itself uploads and changes nothing. Create a draft first if needed. The owner selects images here; do not ask for base64 or public image URLs. The owner then reports "Uploaded N images", and the card shares their URLs as context where the client passes it on; if you do not have them, call list_images rather than asking for the photos again. Then call get_site and update_site to place the URLs where the owner requested. If this client cannot display MCP Apps, give the returned editor link to upload there.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "siteId": "<siteId>"
    },
    "name": "upload_images"
  }
}

Input Schema

NameRequiredDescriptionDefault
siteIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, so the safety profile is covered; the description adds genuinely new context by clarifying that the call itself is a no-op and that the owner, not the agent, performs the selection. It also discloses a client-capability constraint (MCP Apps support) with a fallback path, though it does not say what was returned beyond the editor link.

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

Conciseness3/5

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

The operational flow is front-loaded and each step is actionable, but the middle sentence ('the card shares their URLs as context where the client passes it on') is convoluted and reads as a run-on. The description carries useful content yet could be tightened by several clauses.

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

Completeness4/5

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

For a one-parameter UI-launching tool with annotations covering safety, the description supplies the workflow, the anti-pattern (don't ask for base64/URLs), the recovery path via list_images, downstream placement steps, and a capability fallback. Only the meaning of siteId and any limits on the picker are left uncovered.

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

Parameters2/5

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

Schema description coverage is 0% and the single siteId parameter is never mentioned in the description, so nothing explains which site receives the images or how the draft/site relationship works. The UUID format is visible in the schema, but the description does not compensate for the coverage gap.

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

Purpose4/5

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

States a specific verb and resource — opens an image picker in the conversation for a Stick site — and explicitly reconciles the misleading 'upload' name by saying the call itself uploads and changes nothing. It does not distinguish itself from the closely related prepare_image_upload sibling, leaving that boundary implicit.

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 routes the agent through the whole flow: create a draft first if needed, let the owner select images rather than asking for base64 or public URLs, call list_images instead of re-asking for photos when URLs are missing, then get_site and update_site to place them. It also names the fallback (hand over the returned editor link) when the client cannot display MCP Apps.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources