Skip to main content
Glama
vmware-skills

io.github.zw008/vmware-debug

by vmware-skills
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

incident_timeline

Read-onlyIdempotent

Correlate VMware events into a single incident timeline, rank root-cause hypotheses, and suggest next diagnostic steps to guide troubleshooting.

Instructions

[READ] Correlate already-fetched VMware events into one incident view.

WHEN: use this after you've pulled events for an incident from the data-source skills (vmware-monitor get_events/get_alarms, vmware-aria list_alerts/list_anomalies, vmware-log-insight log_search/log_aggregate, vmware-nsx) — feed them here to find what correlates and where to look next. Not sure which events to pull? Run list_symptom_categories first. This tool does NOT fetch anything itself.

RETURNS: {event_count, window, binning, classification, spikes (strongest anomalous bins), spikes_total, hypotheses (ranked root-cause candidates, each with a suggested_check), next_checks (which skill/tool to run next)}. Read binning for the resolution you were given, and classification for how much of the stream matched nothing — the ranking describes only the part that did.

GOTCHAS: read-only, stateless, no network — nothing is executed. Remediation routes to vmware-aiops (single fix) or vmware-pilot (multi-step). A malformed event returns {error, hint} naming the offending index.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
top_nNoHow many ranked hypotheses come back (default 5). Spikes are capped separately at 20, true count in 'spikes_total'.
eventsYesEvent envelopes, each {ts, source, severity, entity, text, fields}. ts may be ISO-8601, epoch seconds or epoch millis and is required; severity is normalised onto critical/error/warning/ info/unknown, so vendor spellings (fatal, red, warn, yellow, notice, green) are accepted. An entry that cannot be normalised is refused with its index, not skipped. Keep each event's event_type in fields — vmware-monitor's get_events returns it, and the symptom classifier matches it alongside the message. On a modern EventEx the message is generic boilerplate and the eventTypeId is the only thing that says what happened, so dropping it turns a readable event into an uncategorized one.
bin_secondsNoTime-bin width in seconds. Omit and it is chosen from event density off the ladder 1/10/60/300/900/3600/21600/86400, taking the finest width still averaging 4 events per bin.
z_thresholdNoStandard deviations above the mean bin count that mark a spike (default 2.0). Under 3 bins, or a flat series, yields none at any threshold — empty spikes is not "calm".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.13.0
    • changedInput schema / properties / events / description
      Previous value: -"Event envelopes, each {ts, source, severity, entity, text, fields}. ts may be ISO-8601, epoch seconds or epoch millis and is required; severity is normalised onto critical/error/warning/ info/unknown, so vendor spellings (fatal, red, warn, yellow, notice, green) are accepted. An entry that cannot be normalised is refused with its index, not skipped."New value: +"Event envelopes, each {ts, source, severity, entity, text, fields}. ts may be ISO-8601, epoch seconds or epoch millis and is required; severity is normalised onto critical/error/warning/ info/unknown, so vendor spellings (fatal, red, warn, yellow, notice, green) are accepted. An entry that cannot be normalised is refused with its index, not skipped. Keep each event's event_type in fields — vmware-monitor's get_events returns it, and the symptom classifier matches it alongside the message. On a modern EventEx the message is generic boilerplate and the eventTypeId is the only thing that says what happened, so dropping it turns a readable event into an uncategorized one."
    • changedInput schema / title
      Previous value: -"_incident_timeline_implArguments"New value: +"incident_timelineArguments"
  2. Changed5 schema fields changedv1.11.1
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / bin_seconds / description
      Added value: +"Time-bin width in seconds. Omit and it is chosen from event density off the ladder 1/10/60/300/900/3600/21600/86400, taking the finest width still averaging 4 events per bin."
    • addedInput schema / properties / events / description
      Added value: +"Event envelopes, each {ts, source, severity, entity, text, fields}. ts may be ISO-8601, epoch seconds or epoch millis and is required; severity is normalised onto critical/error/warning/ info/unknown, so vendor spellings (fatal, red, warn, yellow, notice, green) are accepted. An entry that cannot be normalised is refused with its index, not skipped."
    • addedInput schema / properties / top_n / description
      Added value: +"How many ranked hypotheses come back (default 5). Spikes are capped separately at 20, true count in 'spikes_total'."
    • addedInput schema / properties / z_threshold / description
      Added value: +"Standard deviations above the mean bin count that mark a spike (default 2.0). Under 3 bins, or a flat series, yields none at any threshold — empty spikes is not \"calm\"."
  3. First observedv1.8.8

TDQS

A5/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/destructive-safe, but the description adds concrete behavioral context beyond them: stateless, no network, nothing executed, malformed events return {error, hint} with the offending index. This is substantial added value rather than a restatement of annotations.

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?

Although long, the description is organized into labeled sections (WHEN, RETURNS, GOTCHAS) with the core purpose front-loaded. Every sentence adds operational information; there is no filler or repetition of schema fields.

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 tool with no output schema, the description fully covers return shape, binned resolution semantics, ranking interpretation, error behavior, and onward routing. Nothing an agent needs to call this tool correctly and interpret results is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description enriches parameters meaningfully: event normalization rules, required event_type retention, bin selection ladder, and the z_threshold flat-series caveat ('empty spikes is not calm'). These details materially change how an agent should populate and interpret parameters.

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 opens with a specific verb and resource: 'Correlate already-fetched VMware events into one incident view.' It clearly differentiates itself from fetching tools by stating it does NOT fetch anything itself, and orients the agent toward sibling list_symptom_categories for prior steps.

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

Usage Guidelines5/5

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

A dedicated WHEN section explicitly says to use this after pulling events from named data-source skills, and tells the agent what to do when unsure which events to pull (run list_symptom_categories first). It also routes remediation to specific siblings, leaving no ambiguity about alternatives.

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