Transcriptor

transcript_health

Check transcription engine health, memory pressure, queue depth, and viewer status before estimating job time or diagnosing stuck tasks.

Instructions

Engine state, real memory pressure, queue depth, degraded tasks.

engine and device say what is actually running here — mlx on Metal, or faster-whisper on cuda or cpu. Worth reading before promising a user how long something will take: the same model differs by an order of magnitude between them. On a machine with a discrete GPU the report also carries vram_*; on unified memory those keys are absent, because there the GPU spends the memory system_available_gb already accounts for.

Also reports whether the transcript download viewer is serving. If viewer.available is false, viewer.error says why — usually the port is already taken by another Transcriptor.

Memory numbers come from the monitor task's most recent sample rather than being measured inline, so this stays a database-and-memory read.

Input Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 15, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and discloses key behaviors: it is a database-and-memory read (implying read-only), memory numbers come from the monitor task's most recent sample rather than being measured inline, and vram keys appear only on discrete GPUs. It could go further by explicitly stating no side effects or permission requirements, but it is substantially transparent.

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 description is front-loaded with a compact list of what it reports, followed by focused explanations of engine/device differences, vram behavior, viewer errors, and memory sampling. Some return-value detail may be redundant with the existing output schema, but the interpretive context largely earns its place.

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?

Given the output schema exists and there are no input parameters, the description is complete enough for correct invocation. It explains the health report's contents, usage context, and hardware-dependent variations. It could mention sibling alternatives, but no critical information is missing.

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?

The tool takes zero parameters, so the baseline is 4. The description does not need to add parameter semantics, and it correctly focuses on output and behavior instead.

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 enumerates the specific health aspects it reports—engine state, memory pressure, queue depth, degraded tasks, viewer status—and clarifies what engine/device mean. It clearly distinguishes the tool's diagnostic scope, but does not explicitly contrast it with sibling tools like transcript_status, so it falls short of a 5.

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 a clear when-to-use scenario: 'Worth reading before promising a user how long something will take.' This is explicit context rather than implied usage. However, it names no alternatives and no exclusions, so it does not reach 5.

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

Deploy Server