Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

upgrade_kiln

Destructive

Updates the Kiln package to the newest version for the user, so they never have to run a pip command. Offers the update, waits for confirmation, and defers while a print is active.

Instructions

Update the Kiln package to the latest version — for the user.

        The upgrade path a person never has to think about. When a newer Kiln is available (or a
        hosted call returns an upgrade-required signal), OFFER to handle it:
        ask "want me to update Kiln for you now?" and call this with
        confirm=True once they agree. Don't make the user run a pip command.

        AGENT CONTRACT (important):
          * NEVER call this while a print is active — wait until it finishes.
            Swapping Kiln mid-print is unsafe.
          * Confirm with the user first; this changes their installed
            software. Pass confirm=True only after they say yes.
          * On success the new version is on disk but the running Kiln still
            has the old code loaded — relay the restart instruction from the
            result so the user applies it at a safe moment (not mid-print).

        Args:
            confirm: Set True to actually perform the update. Called without
                it, this returns the offer to show the user and changes
                nothing.
            force: Override the mid-print safety defer — only when the user
                explicitly insists.

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": "upgrade_kiln"
  }
}

Input Schema

NameRequiredDescriptionDefault
forceNoOverride the mid-print safety defer — only when the user explicitly insists. Default: false.
confirmNoSet True to actually perform the update. Called without it, this returns the offer to show the user and changes nothing. Default: false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.5.1
    • changedInput schema / properties / confirm / description
      Previous value: -"Default: false."New value: +"Set True to actually perform the update. Called without it, this returns the offer to show the user and changes nothing. Default: false."
    • changedInput schema / properties / force / description
      Previous value: -"Default: false."New value: +"Override the mid-print safety defer — only when the user explicitly insists. Default: false."
  2. Changed4 schema fields changedv1.5.0
    • removedInput schema / properties / confirm / default
      Removed value: -false
    • addedInput schema / properties / confirm / description
      Added value: +"Default: false."
    • removedInput schema / properties / force / default
      Removed value: -false
    • addedInput schema / properties / force / description
      Added value: +"Default: false."
  3. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare destructiveHint=true and readOnlyHint=false; the description goes well beyond that by explaining exactly what is mutated (the installed package on disk), that calling without confirm is a no-op that merely returns an offer, that the running process keeps stale code until restart, and that mid-print swapping is unsafe. That is precisely the operational context annotations cannot convey.

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?

Front-loaded with purpose, then a bulleted AGENT CONTRACT that is easy to scan, which suits a tool with safety-critical preconditions. Minor waste exists in the marketing-ish opener ("The upgrade path a person never has to think about") and in the Args block that restates the schema, but the length is largely earned by the safety rules.

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

Completeness5/5

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

For a two-parameter self-update tool with no output schema, everything an agent needs is present: the trigger conditions, the confirmation protocol, the print-safety defer, the force override, and the instruction to relay the restart step from the result. Nothing required to call it correctly is left out.

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 both parameters are already fully documented in structured form, and the description's Args block is nearly verbatim repetition of that text. It adds only light framing (the mid-print safety defer as the thing force overrides), so the baseline 3 applies rather than a higher score.

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?

"Update the Kiln package to the latest version" names a specific verb and a specific resource, and the scope word "package" distinguishes it from the sibling update_machine_firmware, which targets printer firmware rather than the host software. An agent can tell immediately what this does and what it does not touch.

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

Usage Guidelines5/5

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

It states explicit triggers (a newer Kiln is available, or a hosted call returns an upgrade-required signal), the required social step (offer, ask, then pass confirm=True), and a hard prohibition (never while a print is active). The force parameter carries its own exclusion — only on explicit user insistence — so both when-to-use and when-not-to-use are covered without inference.

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

Deploy Server

Other Tools