RunLite

Add files to a multi-part deploy

upload_files

Idempotent

Adds files to an open upload, up to 50 per call. A path sent again replaces the earlier file at that path. Each file is checked as it arrives (path, type, size). Returns how many files the upload now holds and their total size. Nothing goes live until the upload is published.

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": {
      "uploadId": "<uploadId>",
      "files": "<files>"
    },
    "name": "upload_files"
  }
}

Input Schema

Name	Required	Description	Default
`files`	Yes
`uploadId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 25, 2026

addedInput schema / properties / files / items / properties / content / description
```
Added value: +"Required unless fromUpload is given."
```

addedInput schema / properties / files / items / properties / fromUpload

Added value: +{
+  "description": "An imageId from list_uploads, in place of content: that photo as it was processed. The path needs its format's extension: .jpg or .jpeg for a JPEG, .png for a PNG, .webp for a WebP image.",
+  "type": "string"
+}

changedInput schema / properties / files / items / required

Previous value: -[
-  "path",
-  "content"
-]New value: +[
+  "path"
+]

First observedOct 22, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well past the annotations: adds a 50-file batch cap, states that resending a path replaces the earlier file, notes per-file validation on arrival, describes the return value (count and total size), and clarifies nothing is live until publish. These are exactly the constraints an agent cannot infer from readOnlyHint=false / idempotentHint=true.

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?

Five short sentences, each carrying a distinct fact: scope, limit, replacement rule, validation, return value, and lifecycle. The most decision-relevant facts (what it does, cap) come first with 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?

With no output schema, the description usefully discloses the return payload and covers limits, replacement, and staging semantics for a two-parameter mutation. The one real gap is failure behavior — it says files are 'checked as it arrives' but not whether a bad file rejects the whole call or just that entry.

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?

Top-level schema coverage is 0%, so the description has to compensate, and it does add real meaning for the files array (per-call cap, path-replacement semantics). But uploadId is never explained beyond its name, and the description doesn't say whether path is site-root-relative or how content/fromUpload interact — that detail lives only in the nested schema.

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 ('Adds files to an open upload') plus a hard scope limit ('up to 50 per call'). The closing lifecycle note ('Nothing goes live until the upload is published') implicitly separates it from publish_upload and deploy_site, so the agent can place it in the upload workflow 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 Guidelines4/5

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

'Adds files to an open upload' makes the prerequisite (an upload created via start_upload) clear, and the publish note tells the agent this is a staging step, not a final one. It stops short of naming alternatives or stating when not to use it, so it is clear context without explicit exclusions.

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

All RunLite 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?