Nutcracker

Upload file

upload_file

Get a link to send one image, video or document from your disk (logo, screenshot, product shot, PDF) for a task to work from. Send the file with an HTTP PUT, e.g. curl -T '<upload_url>'; the answer is JSON with the file_id to pass in files on start_task or reply. The link works for 15 minutes. One file_id works for any number of tasks. Up to 100 MB; compress anything larger. Upload an image or video right before the task that uses it: about 20 can wait unsent, and waiting ones also block your human uploading in the app. A large scan can take minutes to read; start_task says when it is not ready yet.

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": {
      "filename": "<filename>"
    },
    "name": "upload_file"
  }
}

Input Schema

Name	Required	Description	Default
`filename`	Yes	Its name with extension, which sets how it is read.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the annotations (readOnlyHint false, destructiveHint false, openWorldHint false) by disclosing the 15-minute link expiry, the 100 MB cap, the ~20 pending-upload queue, the side effect of blocking the human's own uploads in the app, and the latency of large scans. These are exactly the operational constraints an agent needs.

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 purpose and the curl invocation, and every sentence carries operational value. Some sentences are overloaded (the 100 MB limit and the pending-queue warning are run together), which slightly hurts scanability but not enough to call waste.

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?

With no output schema, the description correctly explains the return value (JSON containing file_id) and how to consume it in start_task or reply. Combined with the expiry, size, and readiness notes, nothing an agent needs to call and use this tool is missing.

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 parameter already documents that the extension determines how the file is read, which the description merely echoes. No additional syntax, naming conventions, or edge cases are added, so baseline 3 applies.

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 action (obtain a link to send a file), the resource (one image, video or document from disk), and the downstream consumer (a task to work from, via start_task or reply). This is clearly distinguishable from siblings like create_doc or share_link.

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 strong when-to guidance: upload right before the task that uses it, compress anything over 100 MB, and rely on start_task to signal readiness. It does not name an alternative tool or state when not to use this one, so it falls short of a 5.

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

All Nutcracker tools Inspect

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

Need Help?