Skip to main content
Glama
Sign In

Kaiku

by tech.kaiku.mcp
OverviewDiscussionsAdmin

Set machine price

set_machine_price
Destructive

Price a machine the company's computations run on, from a day on — the company's owner and administrators only. The same machine and 'validFrom' replaces that row; another day adds one, and the earlier row keeps pricing the days before it, so a past month stays at its own price. kind 'monthly' (default) needs monthlyPrice and cores: a machine rented by the month or our own; 'computeCores' says how many of its cores computations get (default all) — only that share can stand idle. kind 'tariff' prices by the second: coreSecond, memoryGiBSecond and gpuRates ('H100=0.001097, A100-80GB=0.000694'). Always say where the price came from: 'source' (the provider's page, or 'invoice'), 'checkedOn', 'basis' (list, invoice, estimate) and, where the plan was only matched by cores and memory, typeAssumed=true. Never invent a price: a machine with no row has no cost.

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": {
      "machine": "<machine>",
      "validFrom": "<validFrom>"
    },
    "name": "set_machine_price"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNo'monthly' (default) or 'tariff'.
noteNoHow the price was arrived at — an estimate's formula.
planNoThe provider's plan, e.g. 'AX42', 'CPX52'.
basisNo'list' (default), 'invoice' or 'estimate'.
coresNomonthly: its cores (threads where the runner counts threads).
sourceNoWhere the price was read: the page's address, or 'invoice'.
machineYesThe machine as its runner reports it, e.g. 'kimmy', 'ax42', 'modal'.
currencyNoCurrency of every price on the row: 'EUR', 'USD' (default).
gpuRatesNotariff: GPU-second prices by type, 'H100=0.001097, L4=0.000222'.
providerNoWho rents it out — 'Hetzner', 'Modal' — or 'own'.
checkedOnNoThe day the source was looked at, YYYY-MM-DD.
memoryGiBNoIts memory in GiB, for the record.
validFromYesThe first day this price is in force, YYYY-MM-DD.
coreSecondNotariff: one core for one second.
typeAssumedNoTrue where the plan was matched by cores and memory, not confirmed.
computeCoresNomonthly: how many of the cores computations get; default all.
monthlyPriceNomonthly: what the whole machine costs a month.
memoryGiBSecondNotariff: one GiB of memory for one second.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations declare destructiveHint=true, and the description earns credit beyond that by explaining exactly what is destroyed and what survives: the same machine and validFrom replaces that row, a different day adds one, and the earlier row keeps pricing preceding days. It also states the permission requirement and the integrity rule 'Never invent a price: a machine with no row has no cost.'

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 purpose and the versioning rule are front-loaded, and almost every clause carries information. The long em-dash-chained sentences and quoted example rates make it denser than it needs to be, slightly hurting scanability.

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?

For an 18-parameter mutation tool with no output schema, it covers the essential semantics: the two pricing modes, the row-versioning behavior, permissions, and provenance fields. It says nothing about the return value or failure behavior, which is the remaining gap.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: monthly requires monthlyPrice and cores, computeCores determines how much can stand idle, tariff needs coreSecond/memoryGiBSecond/gpuRates with a format example, and typeAssumed should be set when a plan was matched only by cores and memory. It leaves note, plan, provider, memoryGiB and currency to the schema, so not a 5.

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 ('Price a machine the company's computations run on, from a day on') and adds the scope that matters: owner and administrators only. An agent can distinguish it from list_machine_prices and delete_machine_price purely from the verb and the stated effect.

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?

Gives clear context for when to use it: replacing an existing row versus adding a new one by choosing the same machine + validFrom, and which 'kind' applies to monthly vs per-second pricing. It lacks explicit steering to siblings (no naming of delete_machine_price or list_machine_prices) and gives no exclusions, so it stops 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.

All Kaiku toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources