Skip to main content
Glama

Upload an image or PDF

upload_asset

Upload one JPEG, PNG, GIF, WebP or PDF up to 10 MB to the connected blog. Images are limited to 32 megapixels and 8000 pixels per dimension. Supply exactly one conversation file or direct public HTTPS source_url. Returns a public URL. Link PDFs from post or page HTML. Image URLs can also be used as featured or gallery images. Uploading alone does not edit or publish a post.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "upload_asset"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
source_urlNoDirect public HTTPS URL for an image or PDF. Use file for attachments in ChatGPT.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / source_url / description
      Previous value: -"Direct public HTTPS image URL. Use file for images attached in ChatGPT."New value: +"Direct public HTTPS URL for an image or PDF. Use file for attachments in ChatGPT."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well past the annotations (which only flag openWorldHint=true and destructiveHint=false) by disclosing upload limits (10 MB, 32 MP, 8000 px/dimension), the exact-one-source constraint, and the return value ('Returns a public URL'). The 'does not edit or publish' note clarifies the side-effect boundary that annotations alone would leave ambiguous.

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?

Front-loads formats and limit, then source rules, then output and follow-up usage in five tight sentences with no filler. Each sentence carries a distinct constraint an agent would otherwise have to guess.

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 write tool with no output schema, the description covers inputs, limits, mutual exclusivity and the returned URL, which is enough to call it correctly. Minor gap: nothing is said about failure modes (unsupported format, oversize rejection) or how the returned URL relates to the stored attachment.

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 coverage is 50% with only two top-level params, and the description supplies the critical semantics the schema cannot: exactly one of file or source_url must be provided (schema lists both as optional, required empty). The 'direct public HTTPS' wording duplicates the schema's own description, so it is slightly redundant.

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?

States a specific verb and resource ('Upload one JPEG, PNG, GIF, WebP or PDF ... to the connected blog') and immediately bounds it with size, format and pixel limits. No sibling tool performs uploads, and the closing line ('Uploading alone does not edit or publish a post') separates it from publish_content/update_content.

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?

Gives explicit operational rules: 'Supply exactly one conversation file or direct public HTTPS source_url', plus downstream guidance that PDFs must be linked from post/page HTML and image URLs can serve as featured/gallery images. It does not name an alternative tool for the source-selection decision, but the when-to-use context is clear.

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