Skip to main content
Glama

memory_commit_session

Records end-of-session decisions, errors, and corrections as structured observations for reuse in later sessions.

Instructions

Record end-of-session learnings from an ephemeral agent. Stores decisions, errors, corrections as structured observations.

Call this once when a session ends, with your own summary of it. The server then runs its learning pipeline in the background, and memory_bootstrap_profile serves the result to later sessions. Use memory_store_session to keep the raw conversation turns, and memory_harvest when the server should extract learnings from transcript files itself.

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": {
      "session_id": "<session_id>",
      "agent_id": "<agent_id>",
      "task_summary": "<task_summary>",
      "outcome": "<outcome>"
    },
    "name": "memory_commit_session"
  }
}

Input Schema

NameRequiredDescriptionDefault
errorsNoErrors encountered
outcomeYes
agent_idYesAgent identifier
decisionsNoDecisions made
session_idYesUnique session identifier
task_summaryYesBrief description of what was attempted
belief_updatesNoBelief updates
user_correctionsNoUser corrections

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv13.0.0

TDQS

A4.4/5.0
Behavior4/5

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

Beyond the single destructiveHint=false annotation, the description discloses the key side effect that annotations cannot convey: the server runs a learning pipeline in the background and memory_bootstrap_profile later serves the result, which tells the agent the write has delayed, indirect consequences. It does not cover re-invocation behavior for a duplicate session_id or whether an existing session record is replaced, which is the remaining gap for a write tool.

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?

Two short paragraphs with the core action front-loaded and the sibling routing placed last, where it belongs. Every clause carries information: trigger, storage model, downstream consumer, and the two alternatives.

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 an eight-parameter write tool with no output schema and minimal annotations, the description covers the trigger, the storage semantics, the downstream consumer, and the alternative tools well. It is slightly short of complete because it says nothing about the response or about what happens if the same session is committed twice.

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 88%, so the schema already documents all eight parameters, and the description only restates the categories (decisions, errors, corrections) that map to array properties. It adds no format, sizing, or content guidance for the arrays or for the outcome enum, so baseline 3 applies.

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: record end-of-session learnings from an ephemeral agent, storing decisions, errors and corrections as structured observations. It explicitly separates itself from memory_store_session (raw turns) and memory_harvest (server-side extraction), so an agent can pick the right tool without opening a schema.

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?

Gives an explicit trigger ('call this once when a session ends, with your own summary of it') and names two alternatives with the conditions that select them: memory_store_session for raw conversation turns, memory_harvest when the server should parse transcript files itself.

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