Skip to main content
Glama

PCAP: analyze a capture

pcap_analyze
Read-only

Start a VoIP quality analysis of an uploaded .pcap/.pcapng capture (upload it with kind "pcap"). Reconstructs SIP calls and RTP streams and scores every stream (Sevana MOS from the decoded speech, network MOS, loss, jitter). Returns a job_id; the call waits up to wait_seconds and, if the analysis finished by then, includes the summary. Otherwise poll job_status. Only analysis reports are returned, never decoded audio. Reports include SIP messages and DTMF digits as captured; they are kept for one hour.

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": {
      "upload_id": "<upload_id>"
    },
    "name": "pcap_analyze"
  }
}

Input Schema

NameRequiredDescriptionDefault
upload_idYesupload_id of a pcap upload
statisticsNocompute aggregate statistics across streams (default true)
wait_secondsNowait up to this many seconds for the result (0-55, default 25)

Output Schema

NameRequiredDescriptionDefault
nextNo
errorNo
stageNocurrent stage while running: parsing, audio, sip, ...
job_idYes
statusYes
percentYes
summaryNoset when a PCAP job is done
created_atYes
expires_atNothe result is deleted at this time
finished_atNo
queue_positionNoapproximate place in the queue while queued

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Beyond readOnlyHint/openWorldHint/idempotentHint, the description discloses that the call blocks up to wait_seconds, returns a job_id for later polling, never returns decoded audio, includes SIP messages and DTMF digits as captured, and that reports expire after one hour. Those are exactly the operational facts an agent needs before invoking it.

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?

Short and front-loaded, with the purpose in the first clause and operational caveats after. Sentences are long and clause-heavy (retention, DTMF, polling packed together), but essentially every clause carries actionable information.

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 job-spawning analysis tool, the description covers trigger conditions, blocking/polling behavior, output scope, and retention. An output schema exists, so not restating the return shape is acceptable, and the async pattern is fully explained.

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?

Schema coverage is 100%, so upload_id, statistics and wait_seconds are already documented in the schema. The description adds the blocking semantics of wait_seconds ('the call waits up to wait_seconds and, if the analysis finished by then, includes the summary') but says nothing extra about the statistics flag, so the baseline 3 applies.

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?

Names a specific verb and resource: 'Start a VoIP quality analysis of an uploaded .pcap/.pcapng capture', and details what it produces (SIP call reconstruction, RTP streams, Sevana MOS, network MOS, loss, jitter). It implicitly separates itself from audio-analysis siblings by requiring a 'kind "pcap"' upload and stating 'Only analysis reports are returned, never decoded audio', but it never names an alternative tool outright.

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?

Gives concrete workflow context: upload first with kind "pcap", then it waits up to wait_seconds and, if unfinished, 'poll job_status'. There is no explicit when-not or comparison to sibling report tools such as pcap_full_report, so the alternative-selection guidance is incomplete.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources