Skip to main content
Glama

Conversations (top talkers)

conversations
Read-onlyIdempotent

List top talkers at a chosen network layer to see who communicated with whom, how many frames and bytes moved, and spot busy or unexpected peers.

Instructions

List conversations (top talkers) at one layer: who talked to whom and how much. Use it to find the busy or unexpected peers; for whether TCP connections succeeded use tcp_connections, for media streams rtp_streams. layer is one of ip, ipv6, tcp, udp, sctp or eth. Each row has both endpoints, frames and bytes in each direction, totals, relative start time and duration. filter is an optional display filter that restricts which packets are counted, e.g. gtp or sctp.port == 3868. Sorted by total frames, capped at limit.

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": "conversations"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoSame forms as start
pathYesCapture file (absolute, in an allowed dir) or open_capture handle
layerNoip, ipv6, tcp, udp, sctp or ethip
limitNoMost rows per page
startNoISO 8601, epoch s, +Ns from start, -Ns from end
filterNoExtra display filter, ANDed
offsetNoRows to skip (next_offset)
outputNosummary: all but rows, plus 3 rows (<8 KB)rows
redactNoReplace subscriber identifiers in this result with tokens; ids+ips hides every IP toooff
columnsNoRow keys to keep (frame keys stay)
max_output_kbNoLower output cap, KB

Output Schema

NameRequiredDescriptionDefault
countNo
errorNo
layerNo
offsetNo
windowNo
droppedNo
has_moreNo
returnedNo
next_offsetNo
total_bytesNo
total_foundNo
total_framesNo
conversationsNorows with keys: a, b, frames_a_to_b, bytes_a_to_b, frames_b_to_a, bytes_b_to_a, frames_total, bytes_total, start_rel_s, duration_s
total_matchedNo
display_filterNo
packets_matchedNo
packets_scannedNo
total_is_lower_boundNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare it read-only, idempotent and non-destructive, yet the description still adds real behavior: output is sorted by total frames, capped at `limit`, and each row carries both endpoints, per-direction frames/bytes, totals, relative start and duration. The filter is described as restricting which packets are counted (not merely ANDed), which matters for interpreting the numbers.

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 purpose, then alternatives, then parameter semantics and output shape, then sorting/cap — a sensible ordering with no filler sentences. Minor waste: the `layer` value list duplicates the schema description almost verbatim.

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?

For an 11-parameter tool with an output schema and full annotations, the description covers purpose, routing, filtering semantics, row contents and result ordering, which is enough to call it correctly. It stops short of explaining the redaction or summary/paging modes, which matter for large outputs but are documented in the schema.

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?

With 100% schema coverage the baseline is 3, but the description earns above that by explaining that `filter` scopes the counted packets and giving concrete examples (`gtp`, `sctp.port == 3868`), and by enumerating the `layer` values in the same breath as the row shape. The remaining parameters (redact, output, columns, offset, max_output_kb) are left entirely to the schema despite being non-obvious.

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?

States a specific verb and resource ("List conversations (top talkers) at one layer") plus the scope qualifier "who talked to whom and how much." It explicitly names the sibling tools it is not (tcp_connections, rtp_streams), so an agent can route without opening a schema.

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?

Gives a positive use case ("find the busy or unexpected peers") and two explicit exclusions with the alternative to use instead: tcp_connections for TCP success, rtp_streams for media. That is a complete when/when-not/alternative routing statement.

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