Skip to main content
Glama

Incident summary (what is wrong in this capture)

incident_summary
Read-onlyIdempotent

Analyze an unexamined packet capture to identify what is wrong, rank findings by severity, and return evidence plus the next diagnostic call.

Instructions

Start here on any capture nobody has looked at yet: "what is wrong here?". Runs pcap_info, capture_quality, conversations and the protocol tools the capture carries under one time budget and returns findings ranked by severity (high, medium, low): one plain sentence each, evidence (tool, arguments, frames), confidence and the next_call that shows the detail. Also capture (span, packets, protocols, trust verdict, what the capture cannot show), top_talkers (5), timeline, not_checked (passes skipped and why) and not_analysed (protocols present that no pass reads, each with its next_call). focus: auto (default), web, dns, tls, voip or mobile; budget_s caps the whole call (default and maximum: the server's run timeout). audience="support" adds explanation: the same findings in plain words for a support agent or a ticket (what it means, who to involve, frames, ticket_lines ready to paste). More detail: resource schema://tools/incident_summary.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "path": "<path>"
    },
    "name": "incident_summary"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoSame forms as start
pathYesCapture file (absolute, in an allowed dir) or open_capture handle
focusNoauto, web, dns, tls, voip or mobileauto
startNoISO 8601, epoch s, +Ns from start, -Ns from end
redactNoReplace subscriber identifiers in this result with tokens; ids+ips hides every IP toooff
audienceNoengineer (default) or support: adds plain-language explanationengineer
budget_sNoTime budget for the whole call, seconds

Output Schema

NameRequiredDescriptionDefault
pathNo
errorNo
focusNo
passesNo
windowNo
captureNo
summaryNo
budget_sNo
findingsNorows with keys: kind, severity, text, confidence, evidence, details, next_call
timelineNo
thresholdsNo
explanationNo
not_checkedNo
top_talkersNo
not_analysedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.4.0
    • addedInput schema / properties / audience
      Added value: +{
      +  "default": "engineer",
      +  "description": "engineer (default) or support: adds plain-language explanation",
      +  "type": "string"
      +}
    • addedOutput schema / properties / explanation
      Added value: +{
      +  "type": "object"
      +}
  2. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial behavior beyond them: a single shared time budget across all passes, severity-ranked findings with confidence, and the disclosure fields `not_checked` and `not_analysed` that tell the agent what the run skipped and why. It also explains the `audience="support"` mode and the `redact` implications, so an agent knows exactly what it is getting back.

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?

Front-loaded with the hook and the ranked-findings promise, then organized by output field and by parameter. It is dense and long, but nearly every clause carries new information; a slight tightening of the return-field enumeration would make it cleaner.

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 an orchestrating triage tool with seven parameters, a time budget, and multiple output modes, the description covers entry condition, scope control, output shape, and escape hatches (next_call, not_analysed) and points to a resource schema for deeper detail. An agent has everything needed to invoke it correctly on the first try.

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?

Schema coverage is 100%, so the schema already carries most parameter meaning. The description still adds value beyond it — `budget_s` is described as capping the whole call with the default equal to the maximum (the server's run timeout), and `audience="support"` is explained as producing plain-language `explanation` and pasteable `ticket_lines`, which the schema does not convey.

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 concrete job statement ("what is wrong here?" on an unexamined capture) and immediately names the specific passes it orchestrates (pcap_info, capture_quality, conversations, protocol tools) plus the ranked `findings` output. That makes it clearly distinguishable from every sibling, which are the individual passes this tool bundles.

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 entry condition ("Start here on any capture nobody has looked at yet") and explains how to narrow scope via `focus` (auto/web/dns/tls/voip/mobile) and how to escalate via each finding's `next_call`. It does not state the inverse case — when to skip this and call a single tool directly for a narrow question — which keeps it just short of a 5.

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