Skip to main content
Glama
Komdosh

komnet

by Komdosh
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Read a room's messages, history, or decisions

komnet_read
Read-only

Read messages or settled decisions from a room, using history or superseded options to get full context before re-opening a question.

Instructions

messages (default): the live window of one room, in thread order. Pass since to read further back out of git history instead. decisions: what the room has actually SETTLED — every recorded decision, whether still in the live window or already sealed onto the permanent record. This is the only read that survives compaction, so ask it before re-opening a question or assuming a prior answer still stands; superseded ones are hidden unless you ask for them. Neither the message scope nor komnet_search reaches a sealed decision.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
roomYesRoom id, e.g. 'architecture'
limitNoDefault 50
scopeNoDefault 'messages'
sinceNomessages: read history instead — a git date, e.g. '2026-01-01' or '3 months ago'
threadNomessages: restrict to one thread root id
includeSupersededNodecisions: also return decisions a later one replaced

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.1.2
    • addedInput schema / properties / includeSuperseded
      Added value: +{
+  "description": "decisions: also return decisions a later one replaced",
+  "type": "boolean"
+}
    • addedInput schema / properties / scope
      Added value: +{
+  "description": "Default 'messages'",
+  "enum": [
+    "messages",
+    "decisions"
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / since / description
      Previous value: -"Read history instead: a git date, e.g. '2026-01-01' or '3 months ago'"New value: +"messages: read history instead — a git date, e.g. '2026-01-01' or '3 months ago'"
    • changedInput schema / properties / thread / description
      Previous value: -"Restrict to one thread root id"New value: +"messages: restrict to one thread root id"
  2. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations declare readOnlyHint=true, and the description adds meaningful behavioral context: messages are a live window in thread order, decisions survive compaction, superseded decisions are hidden unless requested. It does not contradict annotations. Minor gap: no mention of pagination or rate limits, but the core behavior is well disclosed.

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?

The description is dense but well-organized, front-loading the default scope and then explaining the decisions scope with its key caveat. It is slightly long but every sentence carries meaningful information; no filler.

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 a read tool with 6 parameters and no output schema, the description covers the main behavioral distinctions and usage context. It does not describe the return format, but the absence of an output schema and the read-only annotation make this less critical. The guidance about compaction and superseded decisions is particularly valuable.

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 description coverage is 100%, so the schema already documents all parameters. The description adds value by explaining the semantic difference between scopes and the meaning of 'since' (read history from git) and 'includeSuperseded' (show replaced decisions), which goes beyond the schema's terse field descriptions.

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 clearly states the tool reads a room's messages, history, or decisions, and distinguishes the two scopes. It explicitly contrasts with komnet_search and notes that decisions are the only read surviving compaction, which differentiates it from sibling tools.

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 description gives explicit guidance: use decisions scope before re-opening a question or assuming a prior answer stands, and notes that neither message scope nor komnet_search reaches sealed decisions. This tells the agent when to use this tool and when not to rely on 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