Skip to main content
Glama
vmware-skills

io.github.zw008/vmware-log-insight

log_aggregate

Read-onlyIdempotent

Aggregate log events into a time series and detect spikes to identify when log volume bursts, enabling targeted follow-up searches on the spike window.

Instructions

[READ] Aggregate matching events into a time series and detect spikes.

WHEN: to find when/whether log volume burst without pulling raw events. Follow up with log_search on the spike window.

RETURNS: {aggregation, bin_width_ms, constraints, bins:[{timestamp_ms, value}], spikes:[{timestamp_ms, value, zscore}]}. A bin is flagged as a spike when it sits at least 2 standard deviations above the mean; a series of fewer than 3 bins, or a flat one, reports no spikes rather than calling everything a spike — so an empty 'spikes' list is not evidence of calm when the window is short. Read-only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
lastNoRelative window ending now — "30m", "2h", "7d" (units s/m/h/d) or a bare number of seconds. Cannot be combined with begin_ms/end_ms. Omit all three and the window defaults to the last hour.
textNoFree-text substring matched with CONTAINS, exactly as in log_search. Omit to aggregate every event in the window.
end_msNoAbsolute window end as epoch milliseconds. Usable on its own; cannot be combined with last.
targetNoLog Insight target name as spelled in ~/.vmware-log-insight/config.yaml. Omit to use that file's default_target — with no default configured, omitting it is an error that lists the configured names.
begin_msNoAbsolute window start as epoch milliseconds. Usable on its own; cannot be combined with last.
aggregationNoThe function applied within each bin — exactly one of COUNT, UCOUNT, AVG, MIN, MAX, SUM, STDDEV, VARIANCE, SAMPLE (lower case is accepted and upper-cased). Anything else raises a ValueError listing the nine. Default COUNT, which answers "how many events per bin" and is what spike detection is normally run on.COUNT
bin_width_msNoWidth of each time bin in milliseconds, must be positive (default 60000 = one minute). It sets the resolution of both the series and the spike test: bins much wider than the burst average it away, bins much narrower make every quiet minute look like noise.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed8 schema fields changedv1.8.14
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / aggregation / description
      Added value: +"The function applied within each bin — exactly one of COUNT, UCOUNT, AVG, MIN, MAX, SUM, STDDEV, VARIANCE, SAMPLE (lower case is accepted and upper-cased). Anything else raises a ValueError listing the nine. Default COUNT, which answers \"how many events per bin\" and is what spike detection is normally run on."
    • addedInput schema / properties / begin_ms / description
      Added value: +"Absolute window start as epoch milliseconds. Usable on its own; cannot be combined with last."
    • addedInput schema / properties / bin_width_ms / description
      Added value: +"Width of each time bin in milliseconds, must be positive (default 60000 = one minute). It sets the resolution of both the series and the spike test: bins much wider than the burst average it away, bins much narrower make every quiet minute look like noise."
    • addedInput schema / properties / end_ms / description
      Added value: +"Absolute window end as epoch milliseconds. Usable on its own; cannot be combined with last."
    • addedInput schema / properties / last / description
      Added value: +"Relative window ending now — \"30m\", \"2h\", \"7d\" (units s/m/h/d) or a bare number of seconds. Cannot be combined with begin_ms/end_ms. Omit all three and the window defaults to the last hour."
    • addedInput schema / properties / target / description
      Added value: +"Log Insight target name as spelled in ~/.vmware-log-insight/config.yaml. Omit to use that file's default_target — with no default configured, omitting it is an error that lists the configured names."
    • addedInput schema / properties / text / description
      Added value: +"Free-text substring matched with CONTAINS, exactly as in log_search. Omit to aggregate every event in the window."
  2. First observedv1.8.9

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint, idempotentHint), the description discloses the spike detection threshold (≥2 standard deviations above the mean), the edge case behavior for short or flat series, and explicitly warns that an empty spikes list is not evidence of calm in short windows. It also declares 'Read-only,' consistent with the 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?

The description is tightly organized into READ, WHEN, and RETURNS sections, with no filler. It front-loads the core purpose, gives a usage signal, and tucks the return shape and edge-case caveat into the RETURNS block — every sentence earns its place.

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?

The description covers purpose, usage context, return shape, and behavioral nuances (spike detection caveats). With 7 parameters fully documented in the schema and no output schema, the description supplies the missing output contract and enough context for an agent to invoke the tool correctly and interpret results, including the important empty-spikes caveat.

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?

The input schema already has 100% parameter description coverage, with detailed explanations for last, text, begin_ms/end_ms, target, aggregation, and bin_width_ms. The tool description does not repeat parameter details, which is appropriate; the baseline of 3 applies because the description adds no parameter-level semantics beyond what the schema already provides.

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: 'Aggregate matching events into a time series and detect spikes.' This clearly distinguishes the tool from siblings like log_search (raw events) and log_fields (schema inspection), and the '[READ]' prefix immediately signals it is a non-mutating operation.

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?

The WHEN section explicitly states the intended scenario: 'to find when/whether log volume burst without pulling raw events,' and directs the agent to 'Follow up with log_search on the spike window.' This names the alternative tool and provides actionable routing guidance rather than leaving the decision implicit.

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/vmware-skills/VMware-Log-Insight'

If you have feedback or need assistance with the MCP directory API, please join our Discord server