Skip to main content
Glama

emet_session_open

Open a dated transcript session and get its session_id for logging exchanges; pass load_id from emet_initialize so the startup page check passes. Refuses opens without a fetched startup page.

Instructions

Open a transcript session. Returns session_id, dated in the configured local time zone (EMET_TIMEZONE, default America/New_York). A slug that already begins with YYYY-MM-DD_ (month 01-12, day 01-31) is not dated again, even when that date is not the local day. A slug whose id is already CLOSED is never reopened: the session opens as -2, -3, ... and the result's notice says so. Pass load_id from your startup pages (startup_page.load_id on every emet_initialize page) so the startup page check runs on your own startup; an open without load_id, or with a page of that startup never fetched, is refused (the refusal says how to pass). After every reply, call emet_transcript_append with that id and the one exchange that just happened. Do not dump the whole chat at close.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "emet_session_open"
  }
}

Input Schema

NameRequiredDescriptionDefault
slugNoShort name for the session, e.g. grok-init. A slug that already begins with YYYY-MM-DD_ (month 01-12, day 01-31) is the base and is not dated again, even when that date is not the local day. Any other slug receives the local day. A closed id still opens as -2, -3, .... Parts are still _verbatim_partN.
load_idNoRequired for the startup page check (by policy; the schema leaves it optional so older hosts can still open): the load_id from `startup_page` on your emet_initialize pages - page 1 returns it, every page carries it, and the last page names it. An open without load_id, or with a page of that load known not fetched, is refused before anything is written (gate startup_pages); the refusal names the exact calls that pass.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.3.2
    • changedInput schema / properties / slug / description
      Previous value: -"Short name for the session, e.g. grok-init"New value: +"Short name for the session, e.g. grok-init. A slug that already begins with YYYY-MM-DD_ (month 01-12, day 01-31) is the base and is not dated again, even when that date is not the local day. Any other slug receives the local day. A closed id still opens as -2, -3, .... Parts are still _verbatim_partN."
  2. Changed1 schema field changedv0.2.2
    • addedInput schema / properties / load_id
      Added value: +{
      +  "description": "Required for the startup page check (by policy; the schema leaves it optional so older hosts can still open): the load_id from `startup_page` on your emet_initialize pages - page 1 returns it, every page carries it, and the last page names it. An open without load_id, or with a page of that load known not fetched, is refused before anything is written (gate startup_pages); the refusal names the exact calls that pass.",
      +  "type": "string"
      +}
  3. First observedv0.1.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already flag a non-readonly, non-idempotent, non-destructive write, but the description adds substantial context beyond them: time-zone-derived dating of the returned id, the rule that pre-dated slugs are not re-dated, that a CLOSED id is never reopened but re-spawned as -2/-3 with a `notice`, and that the startup-page gate refuses before writing anything.

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 and return value, and every sentence carries operational content. It is dense and runs several long clauses together, and the closing 'do not dump the whole chat at close' is more about the close tool than this one, but no sentence is pure padding.

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?

With no output schema, the description steps in to name the returned session_id and the `notice` field, explains the refusal path when load_id is missing, and hands off to the follow-up tool. Nothing needed to call it correctly or interpret the result is missing.

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 both slug and load_id are already documented in the schema, including the YYYY-MM-DD_ dating rule and the '-2, -3' collision rule. The description restates the same semantics for load_id's policy-required-but-schema-optional status rather than adding new meaning, 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?

States a specific verb and resource ('Open a transcript session') and immediately declares the return value (session_id). It implicitly distinguishes itself from emet_session_close and emet_transcript_append by describing the open-then-append workflow, but never explicitly contrasts the siblings.

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?

Explicitly tells the agent what to pass (load_id from startup_page), what happens without it (refusal before anything is written, with a message naming the passing calls), and what to do after every reply (call emet_transcript_append with the id and that one exchange). It even gives a negative rule: do not dump the whole chat at close.

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