Skip to main content
Glama
orcaslicer-mcp

orcaslicer-mcp

Wait for the printer

wait_for_printer
Read-only

Wait until a 3D printer is heated, printing, past the first layer, or finished, then return status as soon as the state is met or the timeout expires.

Instructions

Wait until the printer is heated, printing, past the first layer or finished, checking every 5 seconds.

Returns as soon as it happens (met: true), or at the timeout with the latest status (met: false). It also returns early, with stopped_early saying why, when the printer reports a fault, when the job ends before the point it waits for (a cancelled print, say), or after losing contact ("Lost contact with the printer"). A job that completes successfully while the wait is for 'printing' or 'first_layer_done' counts as met (a one-layer print passes both at once). A met result can carry stopped_early too, for example a job that finished with an error. Waiting for 'finished' when nothing is printing returns at once with the note 'nothing is printing'. Read-only: it never sends commands.

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": {
      "until": "<until>"
    },
    "name": "wait_for_printer"
  }
}

Input Schema

NameRequiredDescriptionDefault
untilYesWhat to wait for. 'heated': every heater with a target is within 3 °C of it. 'printing': extrusion has started. OctoPrint reports no extrusion, so there it means the job is running with the heaters at temperature. 'first_layer_done': the second layer has begun (Klipper only); without layer info from the slicer it is judged from the nozzle height, so it is approximate. 'finished': the job completed, was cancelled or errored.
timeout_sNoSeconds to wait before returning the latest status. Default 300, at most 1800. Call again to keep waiting.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.17

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the readOnlyHint annotation it discloses polling interval, the met/stopped_early result shape, early-return triggers (fault, job ended early, lost contact), the odd case where a completed job satisfies 'printing' or 'first_layer_done', and that met can still carry stopped_early. It also reinforces safety with 'never sends commands', which is additive rather than a bare restatement.

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?

Lead sentence front-loads the core behavior and the return semantics follow in a logical order. It is dense but nearly every clause carries an edge case an agent needs; the parenthetical asides make it a single long paragraph rather than cleanly segmented bullets.

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?

With no output schema, the description fully carries the return contract (met, stopped_early, the 'nothing is printing' note) plus failure modes such as lost contact. For a two-parameter blocking tool this covers everything required to call and interpret it 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?

Schema coverage is 100%, so the enum values are already documented, but the description adds cross-parameter meaning the schema lacks: 'a job that completes successfully while the wait is for printing or first_layer_done counts as met'. The timeout/return interaction is also spelled out. Remaining gap is that it never restates timeout bounds in the body, relying on the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence gives a specific verb and resource plus the exact set of target states ('heated, printing, first_layer_done, finished') and the 5-second poll cadence. It is unmistakably a blocking wait rather than a status read, but it never names the sibling status tools (get_printer_status, get_job_status) that an agent might otherwise choose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description conveys context of use through behavior (it returns early on faults, cancellation, lost contact; 'finished' when idle returns immediately), so an agent can infer when the tool is a poor fit. However, it never explicitly says when to prefer this over polling get_printer_status or how to chain repeated calls beyond the schema's brief note on timeout_s.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.