Skip to main content
Glama
codeofaxel

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

run_speed_schedule

Run, report or stop a layer-based speed schedule on this computer.

Instructions

Run, report or stop a layer-based speed schedule on this computer.

A schedule is a list of ``{"from_layer", "to_layer", "speed_percent"}``
segments.  With ``action="run"`` it starts on the printer that is
printing now, replacing a schedule already running for that printer:
the printer is asked which layer it is on every few seconds and each
segment's speed is set once, as the print reaches it.  It stops on its
own when the print ends, when the printer is found running a different
print, or on ``action="stop"`` (the printer stays at the last speed set).
``action="status"`` reports what has been applied so far.

Only the schedule's shape is checked here.  Which speeds suit this
printer and which layers a speed is unsafe on is decided by Kiln's
served ``set_speed_schedule``, which hands the checked schedule here.

Args:
    schedule: The segments to run (``action="run"`` only).
    printer_name: Which printer.  Omit for the default printer.
    action: ``"run"`` (default), ``"status"`` or ``"stop"``.

Input Schema

NameRequiredDescriptionDefault
actionNoDefault: "run".
scheduleNo
printer_nameNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.5.0

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses the polling cadence ('asked which layer it is on every few seconds'), that each segment's speed is set once, that an existing schedule for the printer is replaced, the auto-stop conditions, and that after action='stop' the printer stays at the last speed set — a real side effect an agent must know.

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 one-line purpose, then lifecycle behavior, then an Args block. Every sentence carries information, though the Args block partially restates what the prose already covered about action and printer_name.

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 a no-annotation, no-output-schema, 3-parameter mutation tool, the description covers side effects, lifecycle, and parameter meaning. The only gap is that action='status' reports 'what has been applied so far' without any hint of its return shape, which an agent may need to interpret results.

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

Parameters5/5

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

Schema coverage is only 33% (only action has a description), so the description must compensate, and it does: it defines the schedule segment shape (from_layer, to_layer, speed_percent), states schedule is only used with action='run', explains printer_name defaults, and enumerates the action meanings. This adds substantial meaning beyond the bare schema titles.

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 set (run/report/stop) against a specific resource (layer-based speed schedule) and scopes it to 'this computer'. It also distinguishes itself from the sibling set_speed_schedule by noting that tool is what validates speeds and hands the schedule here, and from fleet-level speed tools by naming the per-printer scope.

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?

Explains the three action values and the conditions under which the run terminates (print ends, printer starts a different print, or action='stop'), plus the fact that a run replaces any schedule already running for that printer. It stops short of explicitly saying when to prefer set_speed_percent or the fleet speed siblings, but the workflow boundary with set_speed_schedule is 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