Skip to main content
Glama
mcp-feature-test

mcp-feature-test

by linuxrrze

Upload a file from the Dialog Lab (app-only)

dialog_lab_upload

Accepts a base64-encoded file from the Dialog Lab UI, enforces a 10 MiB limit, and returns its size and SHA-256 without storing or logging the content.

Instructions

Called by the Dialog Lab UI with a base64-encoded file. Returns its size and SHA-256; the content is not stored or logged. Limit: 10.00 MiB (UPLOAD_MAX_BYTES). Hidden from the model.

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": {
      "name": "<name>",
      "mimeType": "<mimeType>",
      "data": "<data>"
    },
    "name": "dialog_lab_upload"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataYesStandard base64, no data: prefix
nameYes
mimeTypeYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full disclosure burden and does add real value: content is not stored or logged, the response is size plus SHA-256, and there is a 10.00 MiB cap. It omits permission/auth requirements and what happens on an oversize or malformed base64 payload, which matter for a write-style ingestion tool.

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?

Three short sentences, front-loaded with caller and payload format, then return value, then limit. Every clause carries information; no filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers return values, data-retention behavior, and the size limit, which is substantial for a tool with no output schema. However, two of three parameters remain semantically unexplained and error behavior for oversize input is absent, leaving gaps for a 3-parameter ingestion tool.

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 only 33% -- only "data" is documented in the schema -- and the description covers that parameter implicitly (base64-encoded file) plus the size bound tied to it. It says nothing about what "name" or "mimeType" mean, how they are used, or whether the mimeType is validated, so the coverage gap is only partly compensated.

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?

States a specific verb and resource (upload a file for Dialog Lab) and pins the caller identity ("Called by the Dialog Lab UI"). It does not explicitly differentiate from the sibling upload_file_experimental, which keeps it from a 5.

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 clear scoping guidance in both directions: the caller is the Dialog Lab UI with a base64 payload, and the tool is "Hidden from the model," which signals agents should not select it themselves. No explicit statement of when the UI should use this versus other upload paths, so not a 5.

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