VHGENGINE

by app.railway.up.engine-production-3bdc

health

Read-only

Deep health: DB read+write probe, worker/queue, backup + integrity. Free. Uses the same DB, backup, offsite, and integrity probes as GET /health; status is "ok" only when the DB reads and writes. Returns status/time/LLM, outcome, queue, backups, integrity, running synthesis and delivery postures, commission/source/extract readers, profile readiness, and source writer state. Readable schema 3 proves codec support only; readiness separately proves this process has the exact authorization, private queue, deletion, and immutable-lineage substrate. llm_configured never calls an LLM; check job_worker_alive before start_generate_job.

Input Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Output Schema

TableJSON Schema

Name	Required	Description
`time`	No	Server time, ISO-8601 UTC.
`status`	No	'ok' only when the DB both READS and WRITES (a write probe, not just a ping); 'unavailable' otherwise.
`offsite`	No	Off-volume upload health: {enabled, last_upload_at, last_status, remote_retained}. In-memory, no live S3 call. Null when status is unavailable.
`version`	No	Server version.
`build_sha`	No	Exact deployed Git commit, or null when the platform cannot prove one.
`integrity`	No	Weekly PRAGMA quick_check result: {last_check_at, ok}, both null before the first check has ever run. Null (the whole object) when status is unavailable.
`backup_count`	No	How many daily backups are retained. Null when status is unavailable.
`last_backup_at`	No	Newest nightly backup's timestamp, ISO-8601 UTC. Null before the first backup runs, or when status is unavailable.
`llm_configured`	No	Whether an LLM key is configured. false means smart/research are unavailable and mode=auto resolves to instant. A pure config read, never a live call.
`job_queue_depth`	No	Jobs queued and not yet claimed, across all accounts. Null when status is unavailable.
`job_worker_alive`	No	Whether this deployment runs the job worker. FALSE means start_generate_job would queue a job nothing executes: use generate_hooks instead.
`hook_synthesis_enabled`	No	Running source-grounded synthesis flag posture. Other evidence and LLM capability checks still apply when true.
`outcomes_reported_total`	No	Size of the shared outcome corpus (60s-cached COUNT). Null when status is unavailable.
`release_artifact_sha256`	No	SHA-256 of the exact installed Python package bytes and relative paths.
`visible_speaker_required`	No	Whether media-backed opener verification currently requires a visible speaker.
`extract_schema_read_versions`	No	Permanent Extract schema versions this process can decode. A listed version does not enable extraction.
`hook_research_provider_ready`	No	Whether every approved live hook-research capability is present.
`source_lineage_writes_enabled`	No	Whether authoritative source/extract writers are active on this process. ARCH-103A2 intentionally reports false.
`research_intent_writes_enabled`	No	Whether schema-v4 research-intent writers and workers are active. API-105A intentionally reports false while its permanent readers are deployed.
`commission_schema_read_versions`	No	Permanent commission schema versions this process can decode. Schema 3 being listed does not by itself enable profile-bound generation.
`hook_research_provider_prepared`	No	Whether the exact signed provider graph is validated while dispatch may remain closed.
`creator_profile_generation_ready`	No	Whether this process can safely execute exact schema-3 profile commissions: authorization, private queue ownership, deletion races, payload scrubbing, and immutable lineage are enforced. Public profile-reference input fields remain a separate surface contract.
`hook_research_provider_policy_id`	No	Frozen provider runtime policy identity.
`source_asset_schema_read_versions`	No	Permanent SourceAsset schema versions this process can decode. A listed version does not enable ingestion.
`transcript_based_delivery_enabled`	No	Whether this process admits transcript_grounded opener evidence.
`source_metric_schema_read_versions`	No	Permanent source-metric observation schema versions this process can decode without enabling a metric writer.
`hook_research_capability_receipt_id`	No	Exact complete capability receipt identity, null while closed.
`hook_research_provider_policy_sha256`	No	SHA-256 of the frozen provider runtime policy.
`research_result_schema_read_versions`	No	Permanent standalone research result and occurrence schema versions this process can decode without enabling research delivery.
`extraction_result_schema_read_versions`	No	Permanent standalone extraction result and occurrence schema versions this process can decode without enabling extraction delivery.
`hook_research_prepared_capability_receipt_id`	No	Exact target capability identity, null until closed preparation succeeds.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 2, 2026

addedOutput schema / properties / hook_synthesis_enabled

Added value: +{
+  "description": "Running source-grounded synthesis flag posture. Other evidence and LLM capability checks still apply when true.",
+  "type": [
+    "boolean",
+    "null"
+  ]
+}

addedOutput schema / properties / transcript_based_delivery_enabled

Added value: +{
+  "description": "Whether this process admits transcript_grounded opener evidence.",
+  "type": [
+    "boolean",
+    "null"
+  ]
+}

addedOutput schema / properties / visible_speaker_required

Added value: +{
+  "description": "Whether media-backed opener verification currently requires a visible speaker.",
+  "type": [
+    "boolean",
+    "null"
+  ]
+}

Changed2 schema fields changedAug 17, 2026

addedOutput schema / properties / hook_research_prepared_capability_receipt_id

Added value: +{
+  "description": "Exact target capability identity, null until closed preparation succeeds.",
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / hook_research_provider_prepared

Added value: +{
+  "description": "Whether the exact signed provider graph is validated while dispatch may remain closed.",
+  "type": [
+    "boolean",
+    "null"
+  ]
+}

Changed6 schema fields changedAug 13, 2026

addedOutput schema / properties / build_sha

Added value: +{
+  "description": "Exact deployed Git commit, or null when the platform cannot prove one.",
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / hook_research_capability_receipt_id

Added value: +{
+  "description": "Exact complete capability receipt identity, null while closed.",
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / hook_research_provider_policy_id

Added value: +{
+  "description": "Frozen provider runtime policy identity.",
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / hook_research_provider_policy_sha256

Added value: +{
+  "description": "SHA-256 of the frozen provider runtime policy.",
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / hook_research_provider_ready

Added value: +{
+  "description": "Whether every approved live hook-research capability is present.",
+  "type": [
+    "boolean",
+    "null"
+  ]
+}

addedOutput schema / properties / release_artifact_sha256

Added value: +{
+  "description": "SHA-256 of the exact installed Python package bytes and relative paths.",
+  "type": [
+    "string",
+    "null"
+  ]
+}

Changed4 schema fields changedAug 10, 2026

addedOutput schema / properties / extraction_result_schema_read_versions

Added value: +{
+  "description": "Permanent standalone extraction result and occurrence schema versions this process can decode without enabling extraction delivery.",
+  "items": {
+    "type": "integer"
+  },
+  "type": [
+    "array",
+    "null"
+  ]
+}

addedOutput schema / properties / research_result_schema_read_versions

Added value: +{
+  "description": "Permanent standalone research result and occurrence schema versions this process can decode without enabling research delivery.",
+  "items": {
+    "type": "integer"
+  },
+  "type": [
+    "array",
+    "null"
+  ]
+}

changedOutput schema / properties / source_lineage_writes_enabled / description

Previous value: -"Whether authoritative source/extract writers are active on this process. ARCH-103A intentionally reports false."New value: +"Whether authoritative source/extract writers are active on this process. ARCH-103A2 intentionally reports false."

addedOutput schema / properties / source_metric_schema_read_versions

Added value: +{
+  "description": "Permanent source-metric observation schema versions this process can decode without enabling a metric writer.",
+  "items": {
+    "type": "integer"
+  },
+  "type": [
+    "array",
+    "null"
+  ]
+}

Changed1 schema field changedAug 10, 2026

addedOutput schema / properties / research_intent_writes_enabled

Added value: +{
+  "description": "Whether schema-v4 research-intent writers and workers are active. API-105A intentionally reports false while its permanent readers are deployed.",
+  "type": [
+    "boolean",
+    "null"
+  ]
+}

Changed3 schema fields changedAug 10, 2026

addedOutput schema / properties / extract_schema_read_versions

Added value: +{
+  "description": "Permanent Extract schema versions this process can decode. A listed version does not enable extraction.",
+  "items": {
+    "type": "integer"
+  },
+  "type": [
+    "array",
+    "null"
+  ]
+}

addedOutput schema / properties / source_asset_schema_read_versions

Added value: +{
+  "description": "Permanent SourceAsset schema versions this process can decode. A listed version does not enable ingestion.",
+  "items": {
+    "type": "integer"
+  },
+  "type": [
+    "array",
+    "null"
+  ]
+}

addedOutput schema / properties / source_lineage_writes_enabled

Added value: +{
+  "description": "Whether authoritative source/extract writers are active on this process. ARCH-103A intentionally reports false.",
+  "type": [
+    "boolean",
+    "null"
+  ]
+}

Changed2 schema fields changedAug 10, 2026

addedOutput schema / properties / commission_schema_read_versions

Added value: +{
+  "description": "Permanent commission schema versions this process can decode. Schema 3 being listed does not by itself enable profile-bound generation.",
+  "items": {
+    "type": "integer"
+  },
+  "type": [
+    "array",
+    "null"
+  ]
+}

addedOutput schema / properties / creator_profile_generation_ready

Added value: +{
+  "description": "Whether this process can safely execute exact schema-3 profile commissions: authorization, private queue ownership, deletion races, payload scrubbing, and immutable lineage are enforced. Public profile-reference input fields remain a separate surface contract.",
+  "type": [
+    "boolean",
+    "null"
+  ]
+}

Changed3 schema fields changedAug 2, 2026

addedOutput schema / description

Added value: +"Deep health, including whether an async job submitted now would ever run."

addedOutput schema / properties

Added value: +{
+  "backup_count": {
+    "description": "How many daily backups are retained. Null when status is unavailable.",
+    "type": [
+      "number",
+      "null"
+    ]
+  },
+  "integrity": {
+    "description": "Weekly PRAGMA quick_check result: {last_check_at, ok}, both null before the first check has ever run. Null (the whole object) when status is unavailable.",
+    "type": [
+      "object",
+      "null"
+    ]
+  },
+  "job_queue_depth": {
+    "description": "Jobs queued and not yet claimed, across all accounts. Null when status is unavailable.",
+    "type": [
+      "number",
+      "null"
+    ]
+  },
+  "job_worker_alive": {
+    "description": "Whether this deployment runs the job worker. FALSE means start_generate_job would queue a job nothing executes: use generate_hooks instead.",
+    "type": [
+      "boolean",
+      "null"
+    ]
+  },
+  "last_backup_at": {
+    "description": "Newest nightly backup's timestamp, ISO-8601 UTC. Null before the first backup runs, or when status is unavailable.",
+    "type": [
+      "string",
+      "null"
+    ]
+  },
+  "llm_configured": {
+    "description": "Whether an LLM key is configured. false means smart/research are unavailable and mode=auto resolves to instant. A pure config read, never a live call.",
+    "type": [
+      "boolean",
+      "null"
+    ]
+  },
+  "offsite": {
+    "description": "Off-volume upload health: {enabled, last_upload_at, last_status, remote_retained}. In-memory, no live S3 call. Null when status is unavailable.",
+    "type": [
+      "object",
+      "null"
+    ]
+  },
+  "outcomes_reported_total": {
+    "description": "Size of the shared outcome corpus (60s-cached COUNT). Null when status is unavailable.",
+    "type": [
+      "number",
+      "null"
+    ]
+  },
+  "status": {
+    "description": "'ok' only when the DB both READS and WRITES (a write probe, not just a ping); 'unavailable' otherwise.",
+    "type": [
+      "string",
+      "null"
+    ]
+  },
+  "time": {
+    "description": "Server time, ISO-8601 UTC.",
+    "type": [
+      "string",
+      "null"
+    ]
+  },
+  "version": {
+    "description": "Server version.",
+    "type": [
+      "string",
+      "null"
+    ]
+  }
+}

removedOutput schema / title
```
Removed value: -"healthDictOutput"
```

Changed1 schema field changedJul 20, 2026
- addedInput schema / additionalProperties
```
Added value: +false
```
First observedJul 18, 2026

TDQS

A3.7/5.0

Behavior1/5

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

The description says 'DB read+write probe' and 'status is ok only when the DB reads and writes,' implying the tool performs database writes. This directly contradicts the annotation readOnlyHint=true, making the behavioral disclosure unreliable. Annotation Contradiction.

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 core purpose is front-loaded and the description is dense with useful details. The enumerated return-field list and overlap with the 'same probes as GET /health' phrasing make it slightly heavier than necessary, but most content 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?

With an output schema present and no parameters, the description goes beyond the minimum by explaining readiness vs codec support, source writer state, and the job_worker_alive caveat. However, the readOnlyHint contradiction means a key behavioral aspect is not reliably communicated.

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?

This tool has zero parameters and schema description coverage is 100%, so no parameter-level meaning is needed. The baseline of 4 applies because parameter semantics are trivially satisfied.

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?

The description immediately identifies this as a deep health probe covering DB read/write, worker/queue, backup, and integrity, and clarifies the status semantics ('ok' only when the DB reads and writes). This clearly distinguishes it from sibling tools like get_job or wait_for_job.

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 provides operational context by referencing GET /health probes and gives an explicit cross-tool instruction: check job_worker_alive before start_generate_job. It does not enumerate when not to use this tool, but the usage context is otherwise clear.

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

All VHGENGINE tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?