Skip to main content
Glama
DustinTrap

kvm-pilot

by DustinTrap
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

classify_screen

Read-onlyIdempotent

Determine the current boot or run phase shown on a remote machine's screen, read-only, via server vision or local on-device gates for power-off, no-signal, and boot-progress checks.

Instructions

Classify the current screen's boot/run phase (read-only).

Uses the server-side vision backend when configured; cheap on-device gates (power-off, no-signal, boot-progress, OCR rules) resolve with no credentials at all. Return shapes:

  • server-side / cheap-gate → a dict with mode="server" + phase fields.

  • no server vision → caller-side fallback, a [json_text, Image] list: classify the image yourself against the system_prompt / phases in the JSON block.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hintNoOptional context for the vision backend, e.g. what you expect on screen ('Fedora installer, language page').
profileNoProfile name from ~/.config/kvm-pilot/config.toml selecting which KVM/BMC (and its managed host) this call targets. Omit to use the server's default (KVM_PILOT_PROFILE).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.0.0
    • addedInput schema / properties / hint / description
      Added value: +"Optional context for the vision backend, e.g. what you expect on screen ('Fedora installer, language page')."
    • addedInput schema / properties / profile / description
      Added value: +"Profile name from ~/.config/kvm-pilot/config.toml selecting which KVM/BMC (and its managed host) this call targets. Omit to use the server's default (KVM_PILOT_PROFILE)."
  2. First observedv0.1.0

TDQS

A3.9/5.0
Behavior5/5

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

With annotations already covering the safety profile, the description still adds substantial context: it discloses that cheap gates resolve with no credentials at all, that server vision is used only when configured, and that a caller-side fallback returns [json_text, Image]. This is exactly the auth/behavior/return-shape information the annotations do not carry.

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?

Purpose is front-loaded, followed by mechanism and then return shapes in a bulleted structure. It is dense but every block earns its place given the dual-mode behavior; only minor tightening is possible.

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 two-optional-param tool with no output schema and an unusual dual-mode contract, the description does the needed work by spelling out both return shapes and the pending caller-side responsibility. It is nearly complete, missing only when-to-use guidance.

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 schema already documents both 'hint' and 'profile' fully. The description adds no parameter-level meaning beyond the schema (it references system_prompt/phases in the return payload, not the inputs), so the baseline 3 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 (Classify) and resource (the current screen's boot/run phase), and even parenthesizes scope with '(read-only)'. No sibling tool (power_state, snapshot, logs, etc.) overlaps this screen-classification role, so an agent can route to it unambiguously.

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

Usage Guidelines2/5

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

The description explains the internal mechanism and return shapes but never states when to reach for this tool over alternatives or what conditions trigger it. There is no 'use this when...' clause and no exclusion criteria; usage is only weakly implied.

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