Skip to main content
Glama

Log this chat

log_chat

Keep a running log of the current conversation in the user's Thread so the next AI knows what happened. Call it empty to get the log path, then pass that path to append new details.

Instructions

Keep a running log of this conversation in the user's Thread (chats//), so the next AI they use knows what happened here. First call: leave chat empty; it returns the log's path. Later calls: pass that path as chat to add what's new. small_things: small questions and quick facts from the chat. saved_to: paths of notes you saved with remember during this chat.

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": {
      "app": "<app>",
      "topic": "<topic>",
      "summary": "<summary>"
    },
    "name": "log_chat"
  }
}

Input Schema

NameRequiredDescriptionDefault
appYes
chatNo
topicYes
summaryYes
saved_toNo
small_thingsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations declare the write/append profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), and the description adds genuinely useful behavior beyond that: the log lives under chats/<date>/ and the tool returns a path on first call that must be reused for subsequent appends. It does not describe failure modes or what happens if a stale path is passed.

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?

Front-loads the purpose, then packs the first-call/later-call protocol and the two specialized parameters into single labeled clauses. Nearly every sentence earns its place and there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return-value detail is not required, and the stateful append workflow is well covered. However, for a 6-parameter mutation tool with 0% schema coverage, leaving `app`, `topic`, and `summary` — all required — undefined is a real gap an agent cannot resolve from structured data.

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 description coverage is 0% across 6 parameters, so the description must carry the load. It explains `chat`, `small_things`, and `saved_to` substantively, but the three required parameters (`app`, `topic`, `summary`) are never described, leaving the most important inputs ambiguous.

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 ('keep a running log of this conversation in the user's Thread (chats/<date>/)') plus a motivating outcome ('so the next AI they use knows what happened here'). That framing also implicitly distinguishes it from the read/search siblings like read_chat and search_chats.

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 an explicit invocation protocol: first call leaves `chat` empty and returns the path, later calls pass that path to append. It also scopes two parameters to specific content types. It stops short of saying when not to log or how this relates to `remember`, `read_chat`, or `search_chats` in a routing sense.

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