Skip to main content
Glama

commit_session_legacy

Records end-of-session learnings from ephemeral agents, storing decisions, errors, and user corrections as structured observations for later retrieval.

Instructions

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

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": "commit_session_legacy"
  }
}

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. Addedv1.0.1

TDQS

A3.5/5.0
Behavior3/5

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

The annotations only declare destructiveHint=false, which the description's 'Record... Stores' framing is consistent with. Beyond that the description does not disclose whether re-committing the same session_id overwrites or appends, whether the call is idempotent, or any permission requirements — meaningful gaps for a persistence tool.

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?

Two tight sentences with the core action front-loaded and no filler. It is arguably over-brief for a tool with eight parameters, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an eight-parameter mutation with four required fields, no output schema, and minimal annotations, the description leaves open the record shape for the array-of-object parameters and the return behavior. It covers the what but not enough of the how for an agent to call it confidently.

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 88%, so the schema already documents parameters, and the description's enumeration of decisions/errors/corrections maps onto the optional arrays. The baseline of 3 is exceeded slightly because it clarifies the semantic purpose of those observation arrays, though it adds nothing about session_id, agent_id, or outcome.

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?

Names a specific verb and resource: 'Record end-of-session learnings' from 'an ephemeral agent', and enumerates the stored content (decisions, errors, corrections). It never differentiates itself from the obvious sibling memory_store_session, and the 'legacy' qualifier in the name is unaddressed in the text.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'End-of-session' and 'ephemeral agent' imply the usage window, so an agent can infer timing. However, there is no explicit when-to-use versus memory_store_session or memory_store, and no stated preconditions such as requiring an active session.

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