vastai-mcp

What is scheduled to die, and is the watchdog alive

teardown_status

Idempotent

Verify teardown ledger and reaper process status to confirm no instances are left running, restarting the reaper if it stopped.

Instructions

The teardown ledger plus the reaper process state. Restarts the reaper if it died while instances are still scheduled. Call this whenever you want proof that nothing will be left running. Returns JSON: {ok, message, next_tool, next_args, ...tool-specific fields}.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`restart_reaper`	No	Restart the watchdog if it is not running, default true

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	Yes	false only when the tool itself failed (bad input, missing key, API error).
`message`	Yes	Human-readable summary to relay to the user.
`next_args`	No	Suggested arguments for next_tool.
`next_tool`	No	Suggested next tool, or null when nothing else is needed.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 15, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already indicate a mutating, idempotent, non-destructive operation. The description adds the key side effect: it restarts the reaper if it died while instances remain scheduled, and it discloses the return shape. This is meaningful context beyond the annotation flags.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four compact sentences: state, side effect, when-to-call, and return format. Every sentence adds a distinct piece of information and the most important behavior is front-loaded.

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 single optional-parameter status tool with an output schema and annotations, the description covers behavior, trigger, side effect, and return envelope. Nothing needed to select or invoke it correctly is missing.

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 coverage is 100%, so the restart_reaper parameter is already documented with its default. The description adds a restart condition ('if it died while instances are still scheduled'), but does not explain or map the parameter by name, so it stays at the high-coverage baseline.

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 description states the tool exposes the teardown ledger and reaper process state and can restart a dead reaper, which is a clear resource and action. It doesn't explicitly contrast with sibling tools, but 'proof that nothing will be left running' makes its role distinctive.

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?

It gives an explicit trigger: 'Call this whenever you want proof that nothing will be left running.' It does not enumerate exclusions or alternatives, but the context is sufficient for routine selection among teardown-related siblings.

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

Deploy Server