Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

check_my_tier

Read-only

Check your current Kiln subscription tier and see why you have it, so you can resolve plan, paywall, or feature-access questions.

Instructions

Check the user's current Kiln subscription tier (Free / Pro / Business / Enterprise) and explain WHY they're on it.

        Use this whenever the user asks any tier / plan / subscription /
        paywall / access question — for example: "what tier am I on",
        "why does it say I need Pro", "do I have to pay for this",
        "what's my plan", "why isn't this Pro feature working", "did
        my subscription not activate", "what's the difference between
        Free and Pro", "I just paid but I'm still seeing free tier",
        "can I use the texture engine", "do I have access to fleet
        management", "what unlocks at Business", "how do I upgrade".

        Walks the live tier-resolution chain on the user's machine
        (OAuth session at ~/.kiln/auth_tokens.json → cached
        entitlement → free-tier fallback) and reports:

          - effective_tier: one of 'free', 'pro', 'business', 'enterprise'
          - resolution_chain: list of every step with which matched
          - matched_source: which step actually determined the tier
          - agent_summary: a plain-English one-liner you can show
            the user verbatim
          - pricing_url: link to send the user if they want to upgrade

        No arguments.  Free-tier safe — does NOT require a license
        to call.  Available to every user.

        JUST PAIRED, AND THE TIER LOOKS STALE?  Try this order, and do
        it yourself rather than handing the user a checklist:

          1. Call ``restart_server``.  This server caches what it
             resolved at startup, so a pairing that happened after it
             launched may simply not be visible to it yet.  A restart
             re-execs in place and is invisible to the user.
          2. Call this tool again.
          3. Only if the tier is STILL stale, ask the user to fully
             quit and reopen their AI app.  That is the one step they
             have to do by hand, so it is the last resort, not the
             first suggestion — and MCP clients differ (some reconnect
             to a restarted server on their own, some do not).

        Report the tier plainly whatever it turns out to be, Free
        included: pairing is not a purchase, and a free account that
        paired successfully must not be told it failed.

        Common interpretation:
          - effective_tier="free", matched_source="kiln_pro_install":
            kiln-pro not installed on this machine.  User can still
            use Pro features through Kiln's servers if signed in.
          - effective_tier="free", matched_source="default":
            kiln-pro installed but no auth — needs `kiln signin`.
          - effective_tier="pro" (or higher) with matched_source=
            "license_manager_resolve" and "oauth_session" matched=True
            in the chain: user is signed in via OAuth and the
            entitlement on file gives them this tier.

        Returns:
            dict with success/effective_tier/resolution_chain/
            matched_source/agent_summary/tier_rank/pricing_url.

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": "check_my_tier"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the readOnlyHint and non-destructive annotations, the description discloses the live tier-resolution chain, the local auth/cache/fallback sources, the no-license requirement, and the fact that restart_server re-execs in place invisibly. It also explains how to interpret common effective_tier and matched_source combinations, which is substantial behavioral context.

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?

The description is front-loaded with purpose and organized into usage, mechanics, troubleshooting, and return-value sections. It is longer than strictly necessary for a zero-argument tool, with some repetition around free-tier safety and availability, but the content is structured and mostly purposeful.

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 zero-parameter, read-only tool without an output schema, the description explains the returned fields, the interpretation of key result combinations, the stale-pairing recovery sequence, and the user-facing reporting guidance. That is complete enough for an agent to call and explain the result correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and an empty input schema, so the baseline is 4. The description correctly says 'No arguments,' and there is no additional parameter semantics to add.

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?

The description states a specific verb and resource: check the user's current Kiln subscription tier and explain why they are on it. It also distinguishes its explanatory resolution-chain behavior from a simple license-status check, so an agent can identify it clearly among the many sibling tools.

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?

It gives an explicit trigger — use this whenever the user asks any tier, plan, subscription, paywall, or access question — and provides several concrete example phrasings. It also supplies a stale-tier troubleshooting order, but it does not explicitly name sibling alternatives such as license_status or state when not to use this tool, so it falls short of a 5.

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