Skip to main content
Glama

ctxstore — memory that follows you across models

Save Session Summary

store_session_summary

Store a compressed summary of this session to preserve continuity for the next one.

Call this before ending a conversation — it is the dream cycle.

Stores a L3 session fact with key='session-latest' (or 'session-latest:claude-code' etc.), auto-archiving the previous version. The next session loads this via load_context().

Include: what was discussed/decided, what changed, what's next/unresolved.

Collaborative takeaways: at natural session-end signals (user says 'okay I'm out', 'let's wrap', 'bye'), draft a one-line takeaway and confirm with the user before storing. Example: "I'll remember: we fixed the rebind bug and decided to skip transcript ingestion for MVP. Sound right?" Edit based on their response, then call store_session_summary. This makes memory consensual and catches mistakes immediately.

Use session_id to scope by client: 'claude-code', 'claude-chat', 'cursor', 'openclaw'

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": {
      "summary": "<summary>"
    },
    "name": "store_session_summary"
  }
}

Input Schema

NameRequiredDescriptionDefault
scopeNoOptional project slug for project-scoped last-wake-epoch watermark (conventions/wake-rehydration-v2:current).
summaryYesWhat happened this session — decisions made, work done, context established
decisionsNoKey decisions made or conclusions reached
next_stepsNoWhat's pending, open questions, what to pick up next session
session_idNoOptional client identifier to scope this summary: 'claude-code', 'cursor', 'claude-chat', 'openclaw'. Defaults to bare session-latest.
contributorsNoOptional list of contributor IDs when multiple agents or users collaborated this session (e.g. ['agent-A', 'chad', 'emily']). Stored in summary for attribution.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only say it is a non-idempotent, non-destructive write; the description adds the behavior that matters — the summary overwrites a fixed key and auto-archives the prior version, is rehydrated by the next session via load_context(), and is meant to be user-confirmed before writing. That side-effect profile is exactly what an agent needs before mutating shared memory.

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 purpose and the call timing, then mechanism, then content guidance, then the confirmation protocol — a sensible order. It runs long and includes a bit of jargon ('it is the dream cycle') that adds no operational value, but the wordy collaborative-takeaway paragraph does carry real behavioral instruction.

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 6-param mutation with no output schema, the description covers what to put in, what happens to the previous record, and how the next session consumes it, so an agent can call it correctly. It stops short of saying what the call returns or how failures/duplicate writes are surfaced, which leaves a small gap.

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 already 100%, so the required summary/decisions/next_steps meanings come from the schema. The description still adds value by explaining how session_id maps to the storage key ('session-latest:claude-code') and by enumerating the content categories to include, which is more than a restatement.

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 ('Store a compressed summary of this session') plus its purpose ('preserve continuity for the next one') and the concrete storage mechanism (an L3 session fact keyed 'session-latest' with the previous version auto-archived). The closing line about load_context() makes clear how this tool pairs with the retrieval sibling, so an agent can distinguish it from generic store_fact/store_facts.

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 explicit timing ('before ending a conversation', 'at natural session-end signals' with example phrases) and a full workflow: draft a one-line takeaway, confirm with the user, edit, then call the tool. What it lacks is an explicit negative/alternative case — it never says when to use store_fact instead of this composite tool.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.