Skip to main content
Glama

upload

DestructiveIdempotent

Copy a local project file to a remote workspace, replacing the remote copy while excluding secrets and project state; on guarded fleets, confirm only after explicit user agreement.

Instructions

Copy one file from the LOCAL project directory to the remote workspace (up to 64 MiB). Replaces an existing remote file. Secrets and project state (.git, .claude, .env*, keys, .mirafleet.yaml) are never transferred. On a guarded fleet you must first ask the user and get their explicit agreement; only then set confirm to the fleet name.

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": {
      "local": "<local>"
    },
    "name": "upload"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoPermission bits (decimal). Default: keep the executable bit.
fleetNoFleet name. Omit to use the default.
localYesLocal file, relative to the local project directory (or absolute inside it). Secrets and project state (.git, .env*, keys, .mirafleet.yaml) are refused.
remoteNoDestination on the remote machine. Default: the same relative path as local.
confirmNoGuarded fleets only: the fleet name, set only after the user explicitly agreed. Never set it on your own.
contextNoContext name. Omit to use the default.
workspaceNoWorkspace id. Omit to use this session's workspace on the fleet.

Output Schema

NameRequiredDescriptionDefault
bytesYes
localYes
whereYes
remoteYes
workspaceYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior5/5

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

The annotations only flag destructive/openWorld/idempotent; the description supplies real behavior: a 64 MiB cap, that an existing remote file is replaced, and an explicit deny-list of secrets and project state (.git, .claude, .env*, keys, .mirafleet.yaml). The guarded-fleet confirmation workflow is a safety trait no annotation conveys.

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?

Four short sentences with no filler; the direction and size limit come first, then overwrite/destruction, then the secret deny-list, then the confirmation gate. Front-loading is exactly right for a destructive operation.

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 an output schema present, return values need not be explained, and 100% parameter coverage plus annotations cover the rest. Minor gaps remain: whether remote parent directories are created and what happens on failure or size-limit rejection are not stated.

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%, so every one of the seven parameters is already documented, including `confirm` and the `remote` default. The description reinforces the guarded-fleet meaning of `confirm` and the local-directory constraint on `local`, but adds no format, path, or mode semantics beyond the schema.

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 gives a specific verb and direction (copy one file from the LOCAL project directory to the remote workspace) plus a size ceiling of 64 MiB and overwrite semantics. The agent can tell this is an upload rather than an edit or a remote-side write, but the description never names the natural counterpart (download) or any sibling it might be confused with.

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?

Usage context is clear: single local file, destination defaults to the same relative path, existing remote file gets replaced. It also adds a strong precondition for guarded fleets (ask the user, get explicit agreement, then set `confirm`). It stops short of explicit exclusions, e.g. when to prefer a bulk copy or how to handle sets of files.

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