Skip to main content
Glama

file_upload_link

Makes a link that takes one file from the user's own computer, so it can be put into Drive, attached to a Jira issue or attached to an email without passing through the conversation. The answer is a link on this service, which opens a page where the user chooses or drops the file, and a one-line command, curl -T with the file's path, that sends the file to it from a terminal. The link takes one file, once, within ten minutes. Sending the file answers a receipt with its name, size and SHA-256, and a file reference, {"type":"upload","upload_id":"..."}, which drive_upload_file, jira_add_attachment and the email tools' attachments take. The file is held in memory for ten minutes after it arrives, goes to one call and is never written to disk. A call to any tool on this service that carries the link itself is refused and the link is cancelled. At most 25 MB, and three upload links or uploaded files waiting at a time.

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": "file_upload_link"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoThe file's name, used when the upload itself carries none. Optional.
max_bytesNoThe largest file the link takes, in bytes. Optional; at most and by default 26214400 (25 MB).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

readOnlyHint=false only tells the agent this is not a pure read; the description supplies the lifecycle facts that matter: single use, ten-minute window, in-memory only and never written to disk, 25 MB cap, and three pending links or files at a time. It also discloses a non-obvious failure mode, that any call carrying the link itself is refused and the link cancelled.

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?

Purpose is front-loaded and every sentence contributes new information, including the receipt shape and the curl command. The prose is dense and runs several clauses together, so it is efficient but slightly harder to scan than a structured layout would be.

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

Completeness5/5

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 covers the return value explicitly: a receipt with name, size and SHA-256 plus a {"type":"upload","upload_id":"..."} reference. It also covers limits, expiry and cancellation, so an agent has everything needed to call it and hand off the result.

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 description's two parameter mentions, the optional name and the 26214400-byte default, essentially restate the schema text rather than adding format or interaction detail. Baseline 3 is appropriate when the schema already carries both parameters.

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?

The first sentence names a specific verb and resource: it makes a link that pulls one file from the user's own computer so it can reach Drive, Jira or email without travelling through the conversation. That is clearly distinct from the sibling file_download_link and from the destination tools it feeds.

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?

The description gives clear context for when to reach for this tool (local files that must not go through the conversation) and names the exact consumers of the resulting file reference, drive_upload_file, jira_add_attachment and the email attachments. It does not state an explicit when-not or name the alternative path an agent should take for small inline content, so it stops short of full routing guidance.

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.