Skip to main content
Glama
Sign In

PixelGlass

by co.pixelglass
OverviewDiscussionsAdmin

Get an upload address

request_upload

On one site of the account, named in site. For a file that you hold: a picture the person gave you in the chat, or one that you made. Answers an upload address and a curl command. Run the command in your sandbox or terminal, once for each file; the address takes any number of files for 15 minutes. Each upload answers the library address and the Markdown to paste (alt) into create_post, replace_post or edit_post, or the url for set_feature_image. Pictures, films, sound and PDF; up to 64 MB. If curl cannot reach the address, ask the person one time to allow the domain allowed_domain in their app's network settings (in Claude: Settings › Capabilities). Never ask the person to add the picture in the editor.

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": {
      "site": "<site>"
    },
    "name": "request_upload"
  }
}

Input Schema

NameRequiredDescriptionDefault
siteYesThe site to work on, as list_sites names it

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior5/5

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

Beyond the annotations (which only mark the tool as non-read-only and open-world), the description discloses the return payload (upload address and curl command), validity window (15 minutes), file size limit (64 MB), supported media types, downstream Markdown output, and a specific network-permission error remedy. That is substantial behavioral context with no contradiction.

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 description is compact and every sentence carries information, but it is written in fragmented, telegraphic sentences ('On one site of the account, named in site') that impede parsing. Front-loading is present but the structure is choppy rather than clean.

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 tool with no output schema, the description explains what is returned and how to use it, including limits and error recovery. The main gap is that it does not position the tool against upload_media, which is important given the sibling list.

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

Parameters3/5

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

The schema already fully documents the single site parameter at 100% coverage, and the description merely restates that the site is named in site. It adds no syntax, format, or selection meaning beyond the schema, so the baseline of 3 applies.

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?

The description identifies the resource (an upload address plus curl command) and the input scenario (a file the agent holds, such as a picture from chat), which is more specific than the title alone. It stops short of distinguishing this from the sibling upload_media tool, so an agent cannot fully rule out the alternative from the description.

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?

It gives a clear use context—files the agent already holds, run the returned curl command once per file—and includes procedural guidance about the 15-minute window and downstream tools. It does not mention when to use upload_media instead or any exclusions, so it is not a 5.

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

All PixelGlass toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources