Skip to main content
Glama
dreamforgestudiollc

EMET

by dreamforgestudiollc
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

emet_initialize

Idempotent

Starts every session by loading prior memory, identity, and voice so the assistant resumes with the right context before replying. Call this first, then follow any page it names.

Instructions

START HERE. Call this FIRST in every session, before answering anything that might have prior context, and always when the user opens with 'initialize', 'start', 'begin', 'hello' or similar. It is the only setup step a user should ever have to know about. A large startup comes in pages: read page_notice first and call again with the page it names until the last page, before replying. If this memory store is new it returns a short interview to run conversationally; if it is established it returns who you are, how you speak (character, when the store keeps one - authoritative on voice for the whole session), who you are serving, and where things were left. The user never needs to know which case applied.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoThe startup is served in pages when it is larger than one result (each page fits under 20,000 bytes). Omit for page 1; every page but the last says which page to ask for next - call again with that page, before replying, until a page says it is the last. "all" returns the whole startup in one result, for a host with no size limit.
load_idNoThe load_id your startup returned in `startup_page.load_id`: every emet_initialize result carries one (each page of a paged startup, the whole startup with page "all" or when it fits one result, and a store that is not set up yet). Pass it with every later page so all pages come from the same startup, and pass the same load_id to emet_session_open so its startup page check runs on this startup.
recent_limitNoHow many recent context entries to return (default 5).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.2.2
    • addedInput schema / properties / load_id
      Added value: +{
+  "description": "The load_id your startup returned in `startup_page.load_id`: every emet_initialize result carries one (each page of a paged startup, the whole startup with page \"all\" or when it fits one result, and a store that is not set up yet). Pass it with every later page so all pages come from the same startup, and pass the same load_id to emet_session_open so its startup page check runs on this startup.",
+  "type": "string"
+}
    • addedInput schema / properties / page
      Added value: +{
+  "description": "The startup is served in pages when it is larger than one result (each page fits under 20,000 bytes). Omit for page 1; every page but the last says which page to ask for next - call again with that page, before replying, until a page says it is the last. \"all\" returns the whole startup in one result, for a host with no size limit."
+}
  2. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations declare idempotent, non-destructive, and readOnlyHint=false; the description adds real behavioral detail beyond that - paginated startup, the read-page_notice/recall loop, load_id threading, and the conditional new-store interview vs. established-store profile. It doesn't explain why readOnlyHint is false despite describing a largely read-oriented setup, a minor gap.

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 the imperative call-to-action and ordered logically (when to call, then paging, then outcomes). It is dense and long, but each sentence carries procedural meaning, so little is wasted.

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 carries the burden and does: it explains paged returns, the load_id contract, both new-store and established-store outcomes, and the sequencing with emet_session_open. An agent has everything needed to call it correctly.

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 coverage is 100%, so the baseline is 3, but the description goes further by explaining the paging workflow ('read page_notice first and call again'), the role of load_id across pages and into emet_session_open, and the defaulting behavior around recent context - value beyond the raw 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?

States a specific action (start/set up the session for a memory store) with front-loaded imperative 'START HERE. Call this FIRST,' and distinguishes its role from siblings like emet_session_open by naming the setup step it owns. An agent immediately knows this is the session-initiation tool.

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 says when to call (first in every session, when the user opens with 'initialize'/'start'/'begin'/'hello', or before any answer relying on prior context) and how to sequence it with emet_session_open and the paging loop. Both the trigger conditions and the alternative/next-step tool are named.

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