Skip to main content
Glama

upload_image

Download an image from a public HTTPS URL, save it to the docs site image folder, and return Markdown to embed it in a tutorial without linking to another site.

Instructions

Download an image from a public https URL and save it in the docs site, so a tutorial can show it without linking to another website. Returns the Markdown to put in the tutorial. Only use images you may reuse (for example under a free license), and credit the author in the tutorial when the license asks for it.

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": {
      "url": "<url>",
      "name": "<name>"
    },
    "name": "upload_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
altNoAlt text describing the image, used in the returned Markdown
urlYesPublic https URL of a JPEG, PNG, GIF or WebP image, at most 5 MB
nameYesWhere to save it in the site's image folder, without an extension, e.g. 'nasi-lemak/basic-plate'
commit_messageNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does disclose the write target (site's image folder), the return value, and licensing obligations. However it never states whether saving overwrites an existing image at the same name, whether the change is committed/published (the presence of commit_message implies a git commit), or what permissions are required. Those are material gaps for a mutation tool with zero annotation coverage.

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

Conciseness4/5

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

Three sentences, front-loaded with the core action, then the return value, then the licensing caveat — each sentence does work. Slightly verbose in the licensing clause ('for example under a free license'), but nothing is wasted.

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

Completeness3/5

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

For a 4-parameter write tool with no annotations and no output schema, the description usefully explains the returned Markdown and the licensing rules. It is still incomplete on overwrite behavior, commit/publish side effects, and auth, which an agent needs before invoking it safely.

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?

Schema coverage is 75% — url, name, and alt are documented in the schema, and the description only indirectly reinforces alt via the Markdown return. The one undocumented parameter, commit_message, gets no explanation anywhere, and the description adds no format or naming rules beyond the schema. Baseline 3 is appropriate at this coverage level.

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 concrete two-step action (download a public https image and save it into the docs site) plus the return value (Markdown for the tutorial). This also resolves the mismatch with the name 'upload_image' by making clear the image is fetched, not uploaded by the caller. No sibling tool (list/read/edit/publish tutorial, deploy_site) does image handling, so it is easy to place.

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 a clear motivating condition: use it so a tutorial can show an image without linking to another website. It also states a usage constraint (only reuse-permitted images, credit the author when the license requires it). It does not name when NOT to use it or point at any alternative (e.g., linking externally instead), so it falls short of the 5 bar.

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