Skip to main content
Glama

Cotlet: upload a file for a tool

cotlet_upload_file

Returns a one-time upload_url and a file_id for a local file (an image for a post, an attachment). The file is sent to upload_url with an HTTP PUT; an argument that takes a file accepts {"file_id": "..."}. Up to 25 MB, the URL takes one stored file (a failed PUT can be sent again). Free. Needs the user's Cotlet API key or sign-in.

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": "cotlet_upload_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoFile name, e.g. photo.jpg.
content_typeNoMIME type, e.g. image/jpeg.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior5/5

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

Beyond the annotations (which only say non-read-only, non-destructive, closed-world), the description discloses the crucial mechanic that the tool does NOT upload the bytes itself — the caller must PUT the file to upload_url — plus the 25 MB ceiling, one-file-per-URL limit, retry-on-failed-PUT allowance, no-cost status, and the auth requirement (API key or sign-in). These are exactly the operational facts an agent cannot get from the schema or annotations.

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?

Four tight sentences, front-loaded with the return values, then the PUT mechanic, then limits and auth. It is dense and information-rich with no filler, though the run-on packing of limits, retry behavior, pricing, and auth into one sentence slightly reduces scannability.

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 no output schema, the description correctly carries the burden of describing returns (upload_url, file_id) and the client-side PUT step, which is essential. The remaining gap is that it never clarifies how the 'local file' is identified when the only parameters are a name and a MIME type — an agent may wonder whether it must supply bytes or a path.

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 description coverage is 100% for both parameters (name, content_type) with examples in the schema itself, so the description adds nothing about them and the baseline applies. Its extra value concerns the returned file_id's downstream use, which is output semantics rather than input-parameter meaning.

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 uses a specific verb and resource (returns a one-time upload_url and file_id for a local file) and even scopes the intended payloads (an image for a post, an attachment). It stops short of differentiating itself from the sibling cotlet_browser_upload, so an agent facing a browser-side file input has no stated basis for choosing between them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied through the example payloads and the downstream contract ('an argument that takes a file accepts {"file_id": "..."}'), which tells the agent where this fits in a workflow. There is no explicit when-not guidance and the obvious alternative, cotlet_browser_upload, is never mentioned, so the selection decision against that sibling is left to inference.

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