Skip to main content
Glama
Sign In

Convert.Online

by online.convert
OverviewDiscussionsAdmin

Convert a file

convert

Convert a file to another format and return a download link. Give it one of: source_url (any URL the server can fetch — the best option when the file is already somewhere reachable) or import_id (from create_upload — the way in for a file on someone's device or in your own sandbox, up to 20 GB). There is deliberately no way to pass the bytes inline: those calls are relayed and routinely never arrive, leaving the person watching a spinner. Settings such as resizing, quality or codecs go in options — call list_options first to get the exact names for the conversion. Runs against your account and counts toward your quota.

Input Schema

NameRequiredDescriptionDefault
optionsNoConversion settings, keyed by the option names from list_options — e.g. {"resize_width_image": 1000, "aspect_ratio_image": true}. Names differ per conversion, so do not guess them.
filenameNoFile name of the source, e.g. "photo.jpg". Required with source_base64 unless input_format is given.
import_idNoId returned by create_upload, after the bytes have been PUT to its upload_url. Use this for local files (up to 20 GB sent straight to upload_url, 5 GB through the upload page).
source_urlNoURL of the file to convert, fetched by our server. Any link reachable from the internet works, including a temporary or signed URL for a file the user attached to this conversation — prefer this whenever you have such a URL, because nothing about the file has to pass through the conversation itself.
input_formatNoSource format (optional; inferred from the file name or URL).
output_formatYesTarget format, e.g. "jpg", "pdf", "mp3".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / import_id / description
      Previous value: -"Id returned by create_upload, after the bytes have been PUT to its upload_url. Use this for local files of any size."New value: +"Id returned by create_upload, after the bytes have been PUT to its upload_url. Use this for local files (up to 20 GB sent straight to upload_url, 5 GB through the upload page)."
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already flag this as a non-read-only, non-idempotent, open-world operation, and the description adds real context: it returns a download link, runs against the caller's account, consumes quota, and caps imports at 20 GB. It does not say whether the call is synchronous or must be polled via the get_job sibling, which is the one behavioral gap an agent would care about.

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?

Front-loaded with the action and the two input paths, with the guidance before the rationale. The aside about relayed calls never arriving and the user watching a spinner is longer than needed to justify the no-inline-bytes rule, but it is confined to one clause.

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?

No output schema exists, and the description compensates by naming the return value (a download link) and the limits on input size. For a six-parameter tool with a nested options object, the main thing left unsaid is the async/job lifecycle implied by the get_job sibling.

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 100%, so the baseline is 3, but the description adds meaning the schema does not: source_url and import_id are alternatives, not complements, and options keys must come from list_options rather than being guessed. Filename, input_format, and output_format are left to the schema, which covers them adequately.

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?

Opens with a specific verb and resource plus the return value: "Convert a file to another format and return a download link." It also distinguishes itself from siblings by name, routing uploads to create_upload and option discovery to list_options.

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 states the two mutually exclusive input paths and the condition that selects each: source_url when the file is already reachable, import_id when the file lives on a device or sandbox. It adds a prerequisite (call list_options before passing options) and an exclusion (no inline bytes).

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

All Convert.Online 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