Skip to main content
Glama
Sign In

LetsBot

by net.letsbot
OverviewDiscussionsAdmin

upload_file

Put a file into LetsBot storage and get back a direct https url plus the filename to pass to send_file / send_group_file / send_image / send_video / send_audio. Two ways in — pass exactly one: source_url when the file is already online (a public link, including a Google Drive "Anyone with the link" share link or a Dropbox link; LetsBot downloads it server-side, max 20 MB), or content_base64 only for a small file you generated yourself and hold the bytes of. Prefer source_url whenever a link exists: large base64 strings do not fit in a tool call. Never pass a Google Drive, Dropbox or OneDrive share link straight to the send tools: those point at a download page rather than at the file, so WhatsApp shows an unopenable "BIN" attachment — run it through this tool first. Each call stores a new copy at a new url — if you already have a url from this tool, reuse it instead of uploading again.

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

NameRequiredDescriptionDefault
filenameYesName INCLUDING the extension, e.g. "invoice-2026-012.pdf". The extension must match what the bytes actually are. Any directory part is discarded; the stored object is given a random name. This name is what WhatsApp shows the recipient, so pass it on to send_file / send_group_file as `filename`. Required for both source_url and content_base64 — a share link's path (/view, /uc) is not a file name.
source_urlNoA public http(s) link to the file; LetsBot downloads it (max 20 MB, 20 s). Google Drive share links (drive.google.com/file/d/<id>/view) and Dropbox links (?dl=0) are converted to their direct download form automatically — the Drive file must be shared as "Anyone with the link". Private, internal and non-http(s) addresses are refused. Use this OR content_base64, not both.
content_base64NoThe file contents, base64-encoded — only for a small file you generated yourself. Max 20 MB after decoding. A "data:...;base64," prefix is accepted and its declared type is ignored — the real type is detected from the bytes. Use this OR source_url, not both.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false and openWorldHint=true; the description adds real context beyond them — server-side download with a 20 MB / 20 s cap, conversion of Drive/Dropbox links to direct-download form, the 'new copy at a new url each call' consequence of non-idempotency, and the concrete failure mode (unopenable 'BIN' attachment on WhatsApp). However, it does not mention authentication or permission requirements for writing into storage despite being a mutation tool.

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

Conciseness5/5

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

Front-loaded with what it does and returns, then usage routing, then the failure mode, then the reuse caveat — a sensible priority order. Despite its length every sentence carries distinct information (limits, link conversion, BIN consequence, no re-upload) and there is no 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?

There is no output schema, and the description compensates by stating exactly what comes back (https url + filename) and what to do with it. Size limits, failure modes and exclusivity are all covered. The only gap is that permission/auth requirements for writing to storage are never stated, which matters for a non-read-only tool.

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 baseline is 3; the description earns an extra point by adding the mutual-exclusivity rule and the 'prefer source_url because large base64 strings do not fit in a tool call' rationale, which is genuine decision guidance not in the schema. Some content (the 20 MB limits, 'use this OR content_base64, not both') is repeated from the schema, so not a 5.

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 verb and resource ('Put a file into LetsBot storage') plus the return value ('direct https url plus the filename') and explicitly names the downstream consumers (send_file / send_group_file / send_image / send_video / send_audio). An agent can distinguish this from the send_* siblings without opening a schema.

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?

Gives an explicit decision rule between the two input modes ('pass exactly one'), a preference ordering ('Prefer source_url whenever a link exists'), and a hard exclusion with the reason ('Never pass a Google Drive, Dropbox or OneDrive share link straight to the send tools'). It also states when not to call it at all ('if you already have a url from this tool, reuse it').

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

All LetsBot 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