Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

kiln_spend_caps_request_order_approval

Request approval for one order over a spend cap and get a challenge ID for the two-step confirmation code.

Instructions

Ask to approve ONE order over the cap (step 1 of 2).

        For an order Kiln refused as over the person's spend cap, when
        they want this order to go ahead without raising the cap for
        good.  Returns a ``challenge_id``; step 2 is
        ``kiln_spend_caps_confirm_order_approval`` with their code.

        Args:
            order_id: The order Kiln refused.
            max_dollars: The order total being approved, in dollars.

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": {
      "order_id": "<order_id>",
      "max_dollars": "<max_dollars>"
    },
    "name": "kiln_spend_caps_request_order_approval"
  }
}

Input Schema

NameRequiredDescriptionDefault
order_idYesThe order Kiln refused.
max_dollarsYesThe order total being approved, in dollars.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.5.1
    • addedInput schema / properties / max_dollars / description
      Added value: +"The order total being approved, in dollars."
    • addedInput schema / properties / order_id / description
      Added value: +"The order Kiln refused."
  2. Addedv1.5.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, which says little about what actually happens. The description adds real behavioral context beyond that: this is a request that yields a challenge_id rather than an executed approval, and a second step with the user's code is required, implying the order does not go through here. It does not say how long the challenge is valid or what happens if the order was not actually over the cap.

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 first sentence front-loads the action and the step number, then the conditional context, then the return value and follow-up. The Args block is largely a restatement of the already-complete schema, so a small amount of the text does not earn its place.

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 tool with an output schema, this covers everything an agent needs: when to call it, what it returns, and the mandatory next step. The Args restatement is redundant but not harmful, and no critical gap remains for correct invocation.

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 the baseline is 3, and the Args block does not exceed it — 'The order Kiln refused' and 'The order total being approved, in dollars' are verbatim the schema descriptions. No added meaning such as currency assumptions, tolerance against the cap, or identity of the person whose cap applies.

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 approve ONE order over the cap') and pins its position in a two-step flow ('step 1 of 2'). The scope qualifier 'ONE order' distinguishes it from a permanent cap raise described in the same sentence, so an agent can separate it from kiln_spend_caps_request_change and kiln_spend_caps_confirm_order_approval without opening a schema.

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?

The trigger condition is explicit: an order Kiln already refused as over the person's spend cap, and the user wants it to proceed without raising the cap permanently. It also names the follow-up step. It stops short of naming kiln_spend_caps_request_change as the alternative for a permanent raise, leaving that routing to inference from the phrase 'without raising the cap for good'.

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