Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

kiln_spend_caps_request_change

Initiates a spend cap increase request, returning current and requested caps plus a challenge ID for review and six-digit authenticator confirmation.

Instructions

Ask to raise the per-order and/or monthly spend cap (step 1 of 2).

        The servers hold the requested change for a few minutes and
        return a ``challenge_id``.  Show the person ``current_caps`` and
        ``requested_caps`` so they can review the change, then ask them
        for the six-digit code from their authenticator app and pass it
        to ``kiln_spend_caps_confirm_change``.

        Args:
            per_order_dollars: New per-order cap; leave unset to keep it.
            monthly_dollars: New monthly cap; leave unset to keep it.
            reason: Optional note kept with the change.

        A refusal says which case it is (chat changes turned off, with
        ``enable_url``; too many attempts, with ``retry_after_seconds``;
        a cap below the minimum).  Relay it as written.

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": "kiln_spend_caps_request_change"
  }
}

Input Schema

NameRequiredDescriptionDefault
reasonNoOptional note kept with the change.
monthly_dollarsNoNew monthly cap; leave unset to keep it.
per_order_dollarsNoNew per-order cap; leave unset to keep it.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.5.1
    • addedInput schema / properties / monthly_dollars / description
      Added value: +"New monthly cap; leave unset to keep it."
    • addedInput schema / properties / per_order_dollars / description
      Added value: +"New per-order cap; leave unset to keep it."
    • addedInput schema / properties / reason / description
      Added value: +"Optional note kept with the change."
  2. Addedv1.5.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare that this is not read-only and not destructive; the description adds substantial context beyond that, namely that the server holds the change for a few minutes and returns a challenge_id, and that refusals carry enable_url, retry_after_seconds, or a minimum-cap reason that must be relayed verbatim. It does not say what happens to a pending request that is never confirmed (expiry behavior), which is the one operational gap.

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 the core action and the two-step framing before any detail, and each paragraph covers a distinct concern (flow, args, refusals). The Args block duplicates the input schema and could be dropped without losing information, which keeps it short of a 5.

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 capability-gated mutation that needs a human in the loop, the description covers the request stage, the review step, the handoff to confirmation, and the failure modes. An output schema exists, so return-value detail is rightly omitted.

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 100% and the description's Args block restates the schema wording almost verbatim ('New per-order cap; leave unset to keep it'), so it adds little meaning beyond what an agent already reads in the properties. Baseline 3 applies when the schema carries the parameter semantics.

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?

States a specific verb and resource ('ask to raise the per-order and/or monthly spend cap') and immediately marks itself as 'step 1 of 2', naming the confirm sibling that finishes the job. An agent can distinguish this from kiln_spend_caps_show and kiln_spend_caps_confirm_change without opening any schema.

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?

Gives explicit sequencing: call this first, present current_caps and requested_caps to the person, collect the six-digit authenticator code, then hand the challenge_id and code to kiln_spend_caps_confirm_change. When-to-use and what-comes-next are both stated, with the refusal branches spelled out.

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