Skip to main content
Glama

Upload from a link

upload_from_url

Turn a hosted file URL into a single-use upload_ref: the server fetches, validates (type/size) and duration-probes it, returning an upload_ref to pass as a run file-input param. This is also the way to feed transcription/speech-to-text models from a URL, since they price by measured input length and a bare URL cannot be measured before the job runs.

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": "upload_from_url"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesa public http(s) URL to an image/video/audio file; it is fetched, validated (type/size) and duration-probed into a single-use upload_ref

Output Schema

NameRequiredDescriptionDefault
noteYes
media_typeYes
upload_refYes
duration_minYes

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true and idempotentHint=false; the description adds real context beyond that by explaining that the server fetches an external URL, validates type/size, and produces a single-use artifact — which is why repeated calls are not idempotent. It stops short of saying what happens when validation fails or what the size limits are.

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?

Two sentences, front-loaded with the core transform and then the rationale for the transcription case. The second sentence is long but every clause (measured input length, unmeasurable bare URL) supports the usage decision, so nothing is filler.

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?

With an output schema present, the description needn't explain return values, and it correctly focuses on the upload_ref handoff to the run file-input param. It is nearly complete for a one-parameter tool; only failure behavior and supported type/size limits are absent.

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 100% and the single url parameter is fully documented in the schema, so the baseline is 3. The description restates the fetch/validate/duration-probe pipeline but adds no syntax, format, or constraint detail beyond what the schema already says.

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 names a specific verb and resource ('Turn a hosted file URL into a single-use upload_ref') and states what the server does with it (fetch, validate type/size, duration-probe). It implicitly separates itself from upload_file by scoping to hosted URLs, but never names that sibling, so differentiation is inferred rather than stated.

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 concrete condition for choosing this tool: feeding transcription/speech-to-text models from a URL, because those price by measured input length and a bare URL cannot be measured pre-run. It lacks an explicit exclusion (e.g., 'use upload_file for local files'), so the when-not side is left implicit.

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