Skip to main content
Glama
dreamforgestudiollc

EMET

by dreamforgestudiollc
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

save_transcript

Saves the full word-for-word dialog of a session, with no summaries. Use it to load a Claude Code CLI transcript from JSONL or to write when a host cannot append after each reply.

Instructions

FALLBACK. The primary path is emet_session_open then emet_transcript_append after every reply; use this only where a host cannot append per reply, or to load a Claude Code CLI session from its JSONL file. Saves the full word-for-word dialog of a session - full transcripts only, no summaries. Pass exchanges (chat hosts) or jsonl_path (CLI). Refused for a session that was closed complete.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sourceNoSource tag - which host produced this write. One name on every write since 2026-09-27.
channelNoAlias of `source` (the older name, kept one release). Prefer `source`.
exchangeNoThe exchange (turn) this write belongs to, counting from 1. A write for exchange n while exchange n-1 was never appended is refused by the session graph until n-1 is appended.
exchangesNoClaude.ai Project mode: full array of exchange objects for this session
jsonl_pathNoCLI mode: absolute path to Claude Code session JSONL file. Tool reads and parses it automatically.
session_idYesUnique session identifier, e.g. 'claude_project_2026-05-23_001'
session_endNoUnix timestamp — session end (optional, defaults to now)
session_startYesUnix timestamp — session start

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.2.2
    • changedInput schema / properties / exchange / description
      Previous value: -"The exchange (turn) this write belongs to, counting from 1. A write for exchange n while exchange n-1 was never appended is flagged by the session graph."New value: +"The exchange (turn) this write belongs to, counting from 1. A write for exchange n while exchange n-1 was never appended is refused by the session graph until n-1 is appended."
  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 already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: the tool is a non-preferred fallback, it accepts two distinct input modes, and it is refused for a session closed as complete — a failure mode the annotations do not convey.

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?

Four dense sentences with the fallback status front-loaded and no filler; every clause carries routing, mode or refusal information. It is packed tightly rather than bloated, though the compression makes it slightly telegraphic.

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?

Covers the key call decisions for an 8-parameter, 2-required, non-idempotent write: when to use it, which parameter family matches which host, and a refusal condition. It does not describe what a successful write returns, but no output schema exists and the primary selection/invocation needs are met.

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 baseline is 3. The description exceeds it by mapping parameters to operating modes ('Pass exchanges (chat hosts) or jsonl_path (CLI)'), which tells the agent which grouping of parameters applies to its host before it reads the schema.

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 concrete verb+resource ('Saves the full word-for-word dialog of a session') and immediately bounds the scope ('full transcripts only, no summaries'). It also distinguishes itself from the sibling emet_transcript_append by naming it as the primary path this tool falls back from.

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?

Front-loads 'FALLBACK' and spells out the preferred alternative (emet_session_open + emet_transcript_append after every reply) and the exact conditions that select this tool instead (host cannot append per reply, or loading a CLI JSONL session). It also names a when-not case: refused for a session already closed complete.

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