Skip to main content
Glama
mcp-feature-test

mcp-feature-test

by linuxrrze

Upload a file (EXPERIMENTAL x-mcp-file)

upload_file_experimental
Read-only

Receive an inline base64 file payload and return its decoded size and SHA-256 digest for validation, without storing the file.

Instructions

EXPERIMENTAL, not part of the MCP spec: a tool whose "file" argument is marked with x-mcp-file, following the draft of the io.modelcontextprotocol/files extension (inline base64 only, no out-of-band upload). Returns the size and SHA-256 of the received file; nothing is stored.

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": {
      "file": "<file>"
    },
    "name": "upload_file_experimental"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileYesThe file (FileInput shape of the experimental io.modelcontextprotocol/files extension)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true, and the description substantiates that by stating nothing is stored and that the response is just size plus SHA-256. It also discloses the transfer constraint (inline base64 only, no out-of-band upload), which the agent cannot infer from the annotations; only the 10 MiB maxSize is left to the schema.

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?

Two sentences, front-loaded with the EXPERIMENTAL caveat, then the shape and the return contract. No filler and nothing repeated from the schema.

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?

For a one-parameter tool with full schema coverage and no output schema, the description covers the essentials: what the argument shape is, that transfer is inline-only, what comes back, and that no state persists. The omission of the 10 MiB size cap in prose is minor since the schema states it.

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 the single nested 'file' object, so the schema already documents id, name, size, digest and mimeType, making 3 the baseline. The description adds the provenance of the shape (the io.modelcontextprotocol/files draft) and rules out out-of-band transfer, but does not explain individual field meanings such as digest algorithm or id uniqueness.

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 names a specific verb and resource (upload a file) and pins down the variant precisely: an experimental tool whose 'file' argument uses x-mcp-file from the draft io.modelcontextprotocol/files extension. It is distinguishable from ordinary file-returning siblings, though it does not name an alternative uploader explicitly.

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?

'EXPERIMENTAL, not part of the MCP spec' implies this is for testing the draft files extension rather than production use, which is useful usage framing. However there is no explicit when-to-use/when-not statement and no named alternative (e.g. dialog_lab_upload or return_files) that the agent should pick instead.

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